© 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. 55806
    Prev
    Next
    INDEX
    Explanations

    language labels and academic terms

    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
    ä¸»é£Ł
    -0.07
    PropertyValue
    -0.07
    idth
    -0.07
    åIJī祥å¦ĤæĦı
    -0.07
    ä¸»æľº
    -0.06
    ãģ©ãĤĤ
    -0.06
    Strip
    -0.06
    Millis
    -0.06
    ä¸ī大
    -0.06
    oda
    -0.06
    POSITIVE LOGITS
    .sym
    0.08
    lais
    0.08
    髦
    0.07
     sop
    0.07
    æ°´åľŁä¿ĿæĮģ
    0.07
    çīµæī¯
    0.07
     sost
    0.07
     Casal
    0.07
    转贴
    0.07
    å½ĵ代
    0.07
    Activations Density 0.006%

    No Known Activations