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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4181
    Prev
    Next
    INDEX
    Explanations

    osteo

    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
    uvre
    -0.07
    Previous
    -0.07
     SEEK
    -0.07
     Condition
    -0.06
    AGMENT
    -0.06
     Unexpected
    -0.06
     *↵↵↵
    -0.06
    ())
↵
    -0.06
     kir
    -0.06
    メイン
    -0.06
    POSITIVE LOGITS
     stalled
    0.08
    🟡
    0.08
     '.',
    0.07
    みたいです
    0.07
     umożliwia
    0.07
     pracownik
    0.07
     đang
    0.07
    .vstack
    0.07
     exactly
    0.07
    בעל
    0.07
    Activations Density 0.007%

    No Known Activations