© 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. 11214
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    ä½İçĿĢ头
    -0.07
     III
    -0.07
    ans
    -0.06
     lo
    -0.06
    itse
    -0.06
    转载请注æĺİ
    -0.06
    ynes
    -0.06
    æĸĹ
    -0.06
    -go
    -0.06
    é£İ头
    -0.06
    POSITIVE LOGITS
    óc
    0.08
    ÅĪa
    0.08
    poon
    0.08
    bitset
    0.08
    orate
    0.08
    oen
    0.08
    omis
    0.08
    pont
    0.08
    <tool_response>
    0.07
     دÙĬر
    0.07
    Activations Density 0.003%

    No Known Activations