© 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. 26464
    Prev
    Next
    INDEX
    Explanations

    presumably

    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
    ingo
    -0.08
    vat
    -0.08
    رÙĩ
    -0.08
    emar
    -0.07
    .proto
    -0.07
     Flesh
    -0.07
    å®ŀè´¨ä¸Ĭ
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    lest
    -0.07
    illion
    -0.07
    POSITIVE LOGITS
    ort
    0.08
    å¥½äºĽ
    0.07
    UIS
    0.07
    çĸijéļ¾
    0.07
    롱
    0.06
     cak
    0.06
    erval
    0.06
    cak
    0.06
     institutional
    0.06
    êµī
    0.06
    Activations Density 0.169%

    No Known Activations