© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 25940
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    code snippets involving mutation/assignment operations, especially attempts to modify immutable structures or otherwise perform invalid operations in code

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    mentions of attempts to mutate immutable data structures (especially modifying, inserting, or appending elements in tuples)

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    坞
    -0.08
    璞
    -0.07
    Կ
    -0.07
    潜力
    -0.07
    iationException
    -0.07
     ولك
    -0.07
    意義
    -0.07
     mogul
    -0.07
     premium
    -0.07
    泯
    -0.06
    POSITIVE LOGITS
    فوض
    0.07
    Ắ
    0.07
     Panther
    0.07
     coordination
    0.07
    ыш
    0.07
    نزل
    0.07
    izo
    0.07
     isFirst
    0.06
     assisting
    0.06
    ementia
    0.06
    Activations Density 0.200%

    No Known Activations