© 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. 57282
    Prev
    Next
    INDEX
    Explanations

    discern

    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
     للم
    -0.07
     Authentic
    -0.07
     district
    -0.07
    Co
    -0.07
    ực
    -0.07
    licher
    -0.07
    ()))↵↵
    -0.06
    뗀
    -0.06
    trait
    -0.06
    Evt
    -0.06
    POSITIVE LOGITS
     eğlen
    0.07
    iphy
    0.07
    .timeScale
    0.07
    🕷
    0.07
    .Reference
    0.07
     lodash
    0.06
    ҏ
    0.06
     onBind
    0.06
    _wheel
    0.06
     PREFIX
    0.06
    Activations Density 0.110%

    No Known Activations