© 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. 22093
    Prev
    Next
    INDEX
    Explanations

    coding punctuation and structure

    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
    ết
    -0.07
    飧
    -0.07
    æľ«
    -0.07
    åıĸæĿIJ
    -0.07
    å¹´æľ«
    -0.07
    æ¡£
    -0.06
    é©»
    -0.06
    aven
    -0.06
    ë¦Ħ
    -0.06
    .setParent
    -0.06
    POSITIVE LOGITS
    æľĭ
    0.08
    amet
    0.07
    åįķä½įåıĤåĬł
    0.07
    alise
    0.07
    enson
    0.07
    _stylesheet
    0.07
    ãĥĵãĤ¹
    0.07
    VERRIDE
    0.07
    GRP
    0.07
    inov
    0.07
    Activations Density 0.541%

    No Known Activations