© 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. 49017
    Prev
    Next
    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    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
    组
    -0.08
    "These
    -0.07
    רצ
    -0.07
    vidia
    -0.07
     ourselves
    -0.07
     osc
    -0.07
    偶
    -0.06
     '/');↵
    -0.06
    UPDATE
    -0.06
     travers
    -0.06
    POSITIVE LOGITS
    Amount
    0.07
     Applying
    0.07
     spotting
    0.07
    _OUTPUT
    0.07
    빰
    0.07
    下行
    0.07
    Votes
    0.06
    _PATH
    0.06
    ฑ
    0.06
    泪
    0.06
    Activations Density 0.030%

    No Known Activations