© 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. 43810
    Prev
    Next
    INDEX
    Explanations

    summary and related formats

    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
    ç´ĭ
    -0.07
     Lah
    -0.07
    ç±½
    -0.07
    纹
    -0.07
    èİ«
    -0.07
    è½
    -0.06
    -spe
    -0.06
    æ¯į
    -0.06
    ahren
    -0.06
    åģĩ
    -0.06
    POSITIVE LOGITS
     summary
    0.10
     afterward
    0.10
    æĢ»ç»ĵåĴĮ
    0.10
     summar
    0.09
     summarized
    0.09
     afterwards
    0.09
     Summary
    0.09
    summary
    0.09
    .summary
    0.08
     checklist
    0.08
    Activations Density 0.020%

    No Known Activations