© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    applies to or includes

    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
    å¤ļ空
    -0.08
    orgia
    -0.07
    æ·ĩ
    -0.07
    åŁ¹åħ»åĩº
    -0.07
    讼
    -0.07
    å°ıèįī
    -0.07
     ÙĪرÙĤ
    -0.07
    ifter
    -0.07
    labs
    -0.07
    è¿Ļä½į
    -0.07
    POSITIVE LOGITS
    延伸
    0.12
     scope
    0.12
    èĮĥåĽ´
    0.12
    åıªè¦ģæĺ¯
    0.12
    scope
    0.12
     Scope
    0.12
    çļĦèĮĥåĽ´
    0.12
    æī©å±ķ
    0.12
     extension
    0.11
    广ä¹ī
    0.11
    Activations Density 0.089%

    No Known Activations