© 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. 113469
    Prev
    Next
    INDEX
    Explanations

    co

    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
    Not in Any Lists

    No Comments

    Negative Logits
     animator
    -0.07
    _sms
    -0.07
     radi
    -0.07
    _BORDER
    -0.07
    튭
    -0.06
    亚马
    -0.06
    -margin
    -0.06
     vidé
    -0.06
     tantra
    -0.06
    _slide
    -0.06
    POSITIVE LOGITS
    <object
    0.07
     json
    0.07
     Loud
    0.07
    ᗷ
    0.07
     numeros
    0.07
    𨱑
    0.07
    뱋
    0.07
    	If
    0.07
     Chore
    0.07
    โหล
    0.06
    Activations Density 0.004%

    No Known Activations