© 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. 16383
    Prev
    Next
    INDEX
    Explanations

    code punctuation or specific sequences like `begin()`

    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
    veren
    -0.09
    ç»ĿæĬĢ
    -0.08
    èĢĮåľ¨äºİ
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.08
    sey
    -0.07
     bì
    -0.07
    ricks
    -0.07
    è§ĦåĪĴå±Ģ
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.07
    زاز
    -0.07
    POSITIVE LOGITS
     ton
    0.08
    æªIJ
    0.07
     k
    0.06
     an
    0.06
     vie
    0.06
    ä»Ģä¹Īåij¢
    0.06
    dition
    0.06
    ata
    0.06
     tip
    0.06
    olib
    0.06
    Activations Density 0.009%

    No Known Activations