© 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. 55576
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    鼻子
    -0.08
     ********
    -0.07
    开拓
    -0.07
    렙
    -0.07
     постоян
    -0.07
    紧紧
    -0.07
    ܘ
    -0.07
    stdout
    -0.07
    Login
    -0.07
     counter
    -0.06
    POSITIVE LOGITS
    .Compile
    0.07
    mandatory
    0.07
     Of
    0.07
    ,F
    0.07
    .They
    0.06
    ruptions
    0.06
    laps
    0.06
     fries
    0.06
     Sapphire
    0.06
     drones
    0.06
    Activations Density 0.072%

    No Known Activations