© 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. 15-RESID-POST-AA
    11. 49602
    Prev
    Next
    INDEX
    Explanations

    substantial

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     겁
    -0.07
    青春期
    -0.07
     instantaneous
    -0.07
    渝
    -0.07
    ytic
    -0.06
     Gan
    -0.06
    菩
    -0.06
    줏
    -0.06
    (Level
    -0.06
    匜
    -0.06
    POSITIVE LOGITS
    	module
    0.08
    Stand
    0.07
    因为我们
    0.07
     México
    0.07
    前线
    0.07
    גבול
    0.07
    elerik
    0.06
    .recycle
    0.06
     שנה
    0.06
    廓
    0.06
    Activations Density 0.002%

    No Known Activations