© 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. 12023
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    人è´Ńä¹°
    -0.07
    иÑĤоÑĢ
    -0.06
    ä½łå¥½
    -0.06
    彦
    -0.06
    Skeleton
    -0.06
    çĮ´
    -0.06
    ykl
    -0.06
     exclu
    -0.06
     ende
    -0.06
    èĢĮåĩº
    -0.06
    POSITIVE LOGITS
    irian
    0.07
    sted
    0.07
    .$.
    0.07
    DED
    0.07
    guna
    0.07
    ä¸ĢçĻ¾å¹´
    0.07
    ä¸Ģç»ı
    0.07
    hear
    0.06
    å¹³åİ¿
    0.06
    Hab
    0.06
    Activations Density 0.001%

    No Known Activations