© 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. 32309
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    á»ħn
    -0.07
    fty
    -0.07
    -at
    -0.07
    .say
    -0.07
    ework
    -0.07
     Ranch
    -0.07
    undry
    -0.07
    æ´
    -0.07
    ä¸įæ²»
    -0.07
    åĨł
    -0.07
    POSITIVE LOGITS
    æľĪä¸ĭ
    0.06
    ãĥ¼ãĥĸ
    0.06
    erre
    0.06
     offs
    0.06
    erbe
    0.06
    าย
    0.06
    yte
    0.06
    (pol
    0.06
    æĦĪæĿ¥æĦĪ
    0.06
     зама
    0.06
    Activations Density 0.111%

    No Known Activations