© 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. 19-RESID-POST-AA
    6. 110231
    Prev
    Next
    INDEX
    Explanations

    ru

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    떼
    -0.07
    <>();↵
    -0.07
     snippet
    -0.07
    Flutter
    -0.07
    achten
    -0.07
    年代
    -0.06
     explored
    -0.06
     BEGIN
    -0.06
    npos
    -0.06
    _pull
    -0.06
    POSITIVE LOGITS
    .createCell
    0.07
     Susan
    0.06
    "net
    0.06
    邯
    0.06
    sortable
    0.06
     Emit
    0.06
    덥
    0.06
     ي
    0.06
    立案
    0.06
    CENT
    0.06
    Activations Density 0.058%

    No Known Activations