© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7230
    Prev
    Next
    INDEX
    Explanations

    whole wheat, rice, blood, trees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lech
    -0.08
    resi
    -0.07
    ewart
    -0.07
    hors
    -0.07
    éth
    -0.07
    ä¸įçĽ¸ä¿¡
    -0.07
    ively
    -0.07
    ellini
    -0.07
    elsius
    -0.07
    achel
    -0.07
    POSITIVE LOGITS
     Integrity
    0.08
    اÙħØ©
    0.08
     integrity
    0.07
    /raw
    0.07
    .raw
    0.07
     grit
    0.07
     intact
    0.07
     اÙĦÙĥاÙħÙĦØ©
    0.07
    大äºĭ
    0.07
    æĿĤç²®
    0.07
    Activations Density 0.015%

    No Known Activations