© 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. 12247
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

    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
    æĻĸ
    -0.07
    ald
    -0.07
    ern
    -0.07
    ine
    -0.06
    alc
    -0.06
    ude
    -0.06
    arty
    -0.06
    tte
    -0.06
    art
    -0.06
     kre
    -0.06
    POSITIVE LOGITS
    |array
    0.09
     ==(
    0.08
     pula
    0.08
    |string
    0.07
    جاÙĩ
    0.07
    ä½łä¹Łåı¯ä»¥
    0.07
    $",
    0.07
    __$
    0.07
    'O
    0.07
    embe
    0.07
    Activations Density 0.129%

    No Known Activations