© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11964
    Prev
    Next
    INDEX
    Explanations

    programming, general terms

    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
    <tool_response>
    -0.08
    onga
    -0.08
    ambat
    -0.08
    éĥ½åıªæĺ¯
    -0.07
    anghai
    -0.07
    ..."
    -0.07
    alloween
    -0.07
    brigen
    -0.07
    :.
    -0.07
    önen
    -0.07
    POSITIVE LOGITS
     infatti
    0.10
     ведÑĮ
    0.09
     enim
    0.09
     nämlich
    0.09
     totiž
    0.08
    oret
    0.08
    两åѦä¸Ģåģļ
    0.08
    åĨħ容åĮħæĭ¬
    0.07
    æĸ°åĬłåĿ¡
    0.07
    åĺĽ
    0.07
    Activations Density 0.131%

    No Known Activations