© 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. 37814
    Prev
    Next
    INDEX
    Explanations

    parenthetical, list, or non-latin text

    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
    INTR
    -0.07
    resco
    -0.07
     Intr
    -0.07
    å½ĵ羣
    -0.07
    enskap
    -0.07
    á»±ng
    -0.07
    íĥģ
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.07
    icke
    -0.07
    _IMP
    -0.07
    POSITIVE LOGITS
    æµģè¿ĩ
    0.07
    CIO
    0.07
     Meredith
    0.07
    igli
    0.07
    æİĴéĻ¤
    0.07
    asti
    0.07
    uit
    0.07
    wards
    0.06
    edig
    0.06
    sea
    0.06
    Activations Density 0.129%

    No Known Activations