© 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. 37192
    Prev
    Next
    INDEX
    Explanations

    Half or midpoint

    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
    话
    -0.08
    werp
    -0.07
     embargo
    -0.07
    _
    -0.07
     plunder
    -0.07
     pass
    -0.07
    帐
    -0.07
                    
↵
    -0.07
    甘肃
    -0.07
    menu
    -0.07
    POSITIVE LOGITS
     السنوات
    0.08
    _sess
    0.08
     должност
    0.07
    쨔
    0.07
    dll
    0.07
     טוב
    0.07
    dür
    0.07
    纹理
    0.07
    (panel
    0.07
    薳
    0.07
    Activations Density 0.126%

    No Known Activations