© 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. 30666
    Prev
    Next
    INDEX
    Explanations

    telecom standards institute ETSI

    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
    apol
    -0.07
    à¸Ħลัà¸ĩ
    -0.07
    _DISABLE
    -0.07
    è¡Ģéĩı
    -0.07
    æĹłè¨Ģ
    -0.07
    abbage
    -0.07
     supermer
    -0.07
    .define
    -0.07
    ä¸įèĢIJ
    -0.06
     tø
    -0.06
    POSITIVE LOGITS
    mts
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    pas
    0.07
    zas
    0.07
     WA
    0.06
    ixo
    0.06
    xbe
    0.06
    xce
    0.06
    au
    0.06
    ilier
    0.06
    Activations Density 0.625%

    No Known Activations