© 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. 39482
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and equations

    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»ħéľĢ
    -0.08
     reused
    -0.07
    åıªéľĢ
    -0.07
     uninterrupted
    -0.06
     ÙħØ·Ùħ
    -0.06
    åĴĮèī¯å¥½çļĦ
    -0.06
    åıªéľĢè¦ģ
    -0.06
    åħ´å¥ĭçļĦ
    -0.06
    磫
    -0.06
    æĹłéļľç¢į
    -0.06
    POSITIVE LOGITS
    è´ŁéĿ¢
    0.12
    ä¸įçIJĨæĥ³
    0.11
    ç³Łç³ķ
    0.11
    æĤ²è§Ĥ
    0.11
     negatively
    0.11
     negatif
    0.11
     unfavor
    0.11
     negativ
    0.11
    ä¸įä½³
    0.11
     негаÑĤивно
    0.11
    Activations Density 0.217%

    No Known Activations