© 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. 83480
    Prev
    Next
    INDEX
    Explanations

    for

    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
    .XtraPrinting
    -0.08
     autoComplete
    -0.08
    MARY
    -0.08
     stools
    -0.07
     realize
    -0.07
    屬於
    -0.07
    🍒
    -0.07
    (images
    -0.07
    _INTERRUPT
    -0.07
    _scheduler
    -0.07
    POSITIVE LOGITS
    TO
    0.07
    හ
    0.07
    cap
    0.07
    AVOR
    0.07
    تأ
    0.07
    ition
    0.07
    tog
    0.07
    υ
    0.07
     ili
    0.06
    ظ
    0.06
    Activations Density 0.074%

    No Known Activations