© 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. 57974
    Prev
    Next
    INDEX
    Explanations

    point resistance threshold equnox

    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
    çļĦæ¯ıä¸Ģ
    -0.07
    assi
    -0.07
    ä¸Ģéĥ¨
    -0.07
    å¾ĢæľŁåĽŀ顾
    -0.07
    å¾ĢæľŁç²¾å½©
    -0.06
    以åĪ©
    -0.06
    outs
    -0.06
    éĤ£ä½łå°±
    -0.06
    à®Łà®©à¯į
    -0.06
    /dir
    -0.06
    POSITIVE LOGITS
    å°±åľ¨è¿Ļ
    0.07
    ewhere
    0.07
     carbohydr
    0.07
    haupt
    0.07
    è¿Ľä¸ĢæŃ¥ä¼ĺåĮĸ
    0.07
    éģĵéķ¿
    0.07
    where
    0.07
     наÑģÑĤÑĥпаеÑĤ
    0.07
    æģ¯
    0.07
    arach
    0.07
    Activations Density 0.013%

    No Known Activations