© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 61541
    Prev
    Next
    INDEX
    Explanations

    Avoiding commitment/answering

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contour
    -0.07
     Sesso
    -0.07
     mimeType
    -0.07
    ki
    -0.07
    Bright
    -0.07
    НО
    -0.06
    .sprite
    -0.06
    感じる
    -0.06
    商品房
    -0.06
    蜞
    -0.06
    POSITIVE LOGITS
     UPC
    0.08
    .Modified
    0.07
     simil
    0.07
    唇
    0.07
     посл
    0.07
    -Jun
    0.07
     될
    0.07
     Webster
    0.07
     jeopardy
    0.07
     Gerald
    0.07
    Activations Density 0.036%

    No Known Activations