© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 113706
    Prev
    Next
    INDEX
    Explanations

    political bias

    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
    Negative Logits
    OST
    -0.08
    john
    -0.07
    잪
    -0.06
    郫
    -0.06
     Struct
    -0.06
    Tony
    -0.06
     Enums
    -0.06
    Ǫ
    -0.06
    禅
    -0.06
    -pt
    -0.06
    POSITIVE LOGITS
    かな
    0.08
    万人次
    0.07
    🎮
    0.07
    💿
    0.07
    墣
    0.07
    되었다
    0.07
     Ke
    0.07
    会造成
    0.07
     SIM
    0.07
     approximately
    0.06
    Activations Density 0.067%

    No Known Activations