© 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. 7-RESID-POST-AA
    11. 11886
    Prev
    Next
    INDEX
    Explanations

    non-English language

    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
    Not in Any Lists

    No Comments

    Negative Logits
     clen
    -0.07
     middleware
    -0.07
    なりません
    -0.07
    首领
    -0.07
     eins
    -0.07
     instantiate
    -0.07
    振动
    -0.06
    手下
    -0.06
    コーヒ
    -0.06
     الإنترنت
    -0.06
    POSITIVE LOGITS
     Tus
    0.07
    continued
    0.07
     Romantic
    0.07
     }];↵↵
    0.06
    🏒
    0.06
    ביק
    0.06
    个百分点
    0.06
    põe
    0.06
    lining
    0.06
     curtain
    0.06
    Activations Density 0.421%

    No Known Activations