© 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. 7-RESID-POST-AA
    11. 42550
    Prev
    Next
    INDEX
    Explanations

    motivation and strength

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    非常喜欢
    -0.08
    DirectoryName
    -0.07
    โดย
    -0.07
    ﮊ
    -0.07
    免除
    -0.07
    locs
    -0.07
    _more
    -0.07
    ㉣
    -0.07
     hvor
    -0.07
    真的很
    -0.07
    POSITIVE LOGITS
    prefer
    0.07
     Gal
    0.07
     Wik
    0.07
    伟
    0.07
     Desc
    0.07
     Historic
    0.07
    культ
    0.07
     Latin
    0.07
     Aging
    0.06
     Quest
    0.06
    Activations Density 0.129%

    No Known Activations