© 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. 30959
    Prev
    Next
    INDEX
    Explanations

    simulator

    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
    缸åĮ¹éħį
    -0.07
     matched
    -0.06
    aad
    -0.06
     adequately
    -0.06
    åı¯ä¸į
    -0.06
    åĮ¹éħį
    -0.06
    åĽŀé¦ĸ
    -0.06
    ä¹Ŀå·ŀ
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.06
    缸åIJĮ
    -0.06
    POSITIVE LOGITS
     nearer
    0.09
     clos
    0.08
    çIJĨæĥ³çļĦ
    0.08
    ä»ĭäºİ
    0.08
    LowerCase
    0.08
    çIJĨæĥ³åĴĮ
    0.08
     closer
    0.08
    æľīèĪĪ趣
    0.08
    èĢģå¸Ī说
    0.08
    å¤ªè¿ľ
    0.07
    Activations Density 0.073%

    No Known Activations