© 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. 42101
    Prev
    Next
    INDEX
    Explanations

    quadratic

    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
     Wander
    -0.08
    JSONException
    -0.07
    县城
    -0.07
    pel
    -0.07
    .handleChange
    -0.07
    Ev
    -0.07
     ).
    -0.07
    usat
    -0.07
    �
    -0.07
    .gt
    -0.07
    POSITIVE LOGITS
     *\
    0.08
    lfw
    0.07
     looks
    0.07
    ellido
    0.07
    .io
    0.06
    食品
    0.06
     него
    0.06
    зо
    0.06
     Tacoma
    0.06
    /dd
    0.06
    Activations Density 0.003%

    No Known Activations