© 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. 8137
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code 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
    zwi
    -0.07
    å¥Īä½ķ
    -0.07
    klen
    -0.07
    stens
    -0.07
     Garr
    -0.06
    æİĴ忧解éļ¾
    -0.06
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.06
    åı¯åĸľ
    -0.06
    ç¨ĭ
    -0.06
    ĥĿ
    -0.06
    POSITIVE LOGITS
     Beij
    0.09
    acia
    0.07
    otate
    0.07
    ellet
    0.07
    åħµçļĦ
    0.07
    edic
    0.07
    aida
    0.07
    εÏģι
    0.07
    enseign
    0.07
    chenk
    0.07
    Activations Density 0.010%

    No Known Activations