© 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. 15-RESID-POST-AA
    11. 53986
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Liber
    -0.07
    🏠
    -0.07
     notably
    -0.07
     rope
    -0.07
    牂
    -0.07
    outube
    -0.07
     propane
    -0.07
     speeds
    -0.07
     Burke
    -0.06
    バー
    -0.06
    POSITIVE LOGITS
    صول
    0.07
    consum
    0.07
    >;↵↵
    0.07
     وكل
    0.07
     существует
    0.07
    �建
    0.07
    typescript
    0.06
    cdecl
    0.06
     recovering
    0.06
    good
    0.06
    Activations Density 0.020%

    No Known Activations