© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27027
    Prev
    Next
    INDEX
    Explanations

    number format

    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
    ë¡Ģ
    -0.07
    rawy
    -0.06
    pany
    -0.06
    éķIJ
    -0.06
     Lago
    -0.06
    åľ¨ç©ºä¸Ń
    -0.06
    éķ¿è¿ľ
    -0.06
    åŃľåŃľ
    -0.06
    ä¸Ľä¹¦
    -0.06
     Compilation
    -0.06
    POSITIVE LOGITS
    entai
    0.07
    acto
    0.07
    åħ°å¾·
    0.07
    PACE
    0.06
    WebpackPlugin
    0.06
    '%(
    0.06
    (right
    0.06
     Sache
    0.06
    KK
    0.06
    _ids
    0.06
    Activations Density 0.214%

    No Known Activations