© 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. 51868
    Prev
    Next
    INDEX
    Explanations

    mid or middle usage

    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
    æĸ°å±Ģ
    -0.08
    Falsy
    -0.08
    goed
    -0.08
    ذة
    -0.08
    udiant
    -0.08
    kening
    -0.07
    arendra
    -0.07
    ieber
    -0.07
    ARIANT
    -0.07
    encial
    -0.07
    POSITIVE LOGITS
    most
    0.08
    eix
    0.08
    re
    0.07
    zaak
    0.07
    -aged
    0.07
    cim
    0.07
    æľ¬å¸ĸ
    0.07
    ieval
    0.07
    Ī
    0.07
    hone
    0.07
    Activations Density 0.040%

    No Known Activations