© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and numbers

    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
    bruck
    -0.09
    enciales
    -0.07
    hak
    -0.07
    æĻĴ
    -0.07
     sublicense
    -0.07
    IEL
    -0.07
    é£İæļ´
    -0.07
    Cx
    -0.07
    INGTON
    -0.06
    halle
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.07
     mot
    0.07
    AMI
    0.07
    åı¦å¤ĸ
    0.07
    acket
    0.07
    agi
    0.07
    azzo
    0.06
    ãĤ»ãĤ¤
    0.06
    æĪĸèĢħ缴æİ¥
    0.06
    amo
    0.06
    Activations Density 0.020%

    No Known Activations