© 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. 61607
    Prev
    Next
    INDEX
    Explanations

    packaging bags, workshop guides, DUI defense, DNA analysis, sorting grain

    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
    æĪĸèĢħ说
    -0.10
    —or
    -0.08
    æĪĸèĢħæĺ¯
    -0.07
     bzw
    -0.07
    纵
    -0.07
    ulo
    -0.07
    ìłģìĿ´ê³ł
    -0.07
    ä¸İ建议
    -0.06
    è¿ĺæĺ¯ä¸į
    -0.06
    arra
    -0.06
    POSITIVE LOGITS
    IX
    0.08
    chino
    0.07
     :\
    0.07
    Ĵáŀ
    0.07
    ãģ«èĩ³
    0.07
    笳
    0.07
     outright
    0.07
    æľĪçĶŁ
    0.07
    æĹ¥çĶŁ
    0.07
    ialis
    0.07
    Activations Density 0.101%

    No Known Activations