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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38950
    Prev
    Next
    INDEX
    Explanations

    doesn't

    np_max-act · gemini-2.0-flash

    negative contractions with n't (the auxiliary/base verb part before 't).

    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
     traged
    -0.07
     mappedBy
    -0.07
     to
    -0.07
    o
    -0.07
    x
    -0.07
    .zoom
    -0.07
    资格
    -0.07
    GameOver
    -0.07
    or
    -0.07
    (object
    -0.07
    POSITIVE LOGITS
     couldn
    0.08
    ,
    0.08
     gaan
    0.08
     wouldn
    0.08
     hadn
    0.08
     Chin
    0.07
     Dios
    0.07
    しています
    0.07
    +n
    0.07
     Ấn
    0.07
    Activations Density 0.106%

    No Known Activations