© 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. 6920
    Prev
    Next
    INDEX
    Explanations

    appraisal

    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
     certainly
    -0.07
    革命
    -0.07
     does
    -0.07
     :↵
    -0.07
    */↵
    -0.07
    (),
    -0.07
    уб
    -0.07
     captivating
    -0.06
     vous
    -0.06
    送出
    -0.06
    POSITIVE LOGITS
    raisal
    0.08
    سكان
    0.07
    compat
    0.07
    Ƨ
    0.07
    idea
    0.07
    iture
    0.07
     amend
    0.07
    	Delete
    0.07
    花椒
    0.07
     predetermined
    0.07
    Activations Density 0.001%

    No Known Activations