© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28129
    Prev
    Next
    INDEX
    Explanations

    ID /questions

    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
    ç®
    -0.09
    .timedelta
    -0.08
    preh
    -0.07
    äºĮçŃī
    -0.07
    bile
    -0.07
     Twe
    -0.07
    å²³éĺ³
    -0.07
    rieve
    -0.07
    gable
    -0.07
    pek
    -0.07
    POSITIVE LOGITS
    çĶŁäºİ
    0.08
    ossi
    0.07
    season
    0.07
    uito
    0.07
    annis
    0.07
    åģ¶
    0.07
     Ministère
    0.07
    itto
    0.06
    æĸ°å©ļ
    0.06
     denn
    0.06
    Activations Density 0.015%

    No Known Activations