© 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. 80300
    Prev
    Next
    INDEX
    Explanations

    TOP

    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
    .parseInt
    -0.07
    党委
    -0.07
     ass
    -0.07
    �
    -0.07
     вполне
    -0.07
     mAuth
    -0.07
    🧑
    -0.07
     grad
    -0.06
    jspx
    -0.06
    .parseFloat
    -0.06
    POSITIVE LOGITS
     posture
    0.07
    אוניב
    0.07
    _('
    0.06
     pasture
    0.06
    olución
    0.06
    椅子
    0.06
    时段
    0.06
    пло
    0.06
    :↵↵↵↵↵↵
    0.06
    焦虑
    0.06
    Activations Density 0.001%

    No Known Activations