© 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. 29000
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and clauses

    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
    ä¹ĭæ¯į
    -0.09
    uskan
    -0.08
    whatever
    -0.08
    æıIJä¾Ľä¸ĵä¸ļçļĦ
    -0.08
     whatever
    -0.08
    ugend
    -0.08
    usco
    -0.08
    ä¼ĺå¼ĤçļĦæĪIJ绩
    -0.08
    æ±Łè·¯
    -0.08
    USR
    -0.08
    POSITIVE LOGITS
    æŃ£ç¡®çļĦæĺ¯
    0.10
    éĶĻ误çļĦæĺ¯
    0.10
    羣æŃ£
    0.09
    ä¸įæŃ£ç¡®çļĦæĺ¯
    0.09
     most
    0.09
    å½ĵå±ŀ
    0.08
    ãĤĭãģ®ãģ¯
    0.08
    çļĦè¿ĺæľī
    0.08
    çļĦä¸Ģ项æĺ¯
    0.07
    ãģªãģ®ãģ¯
    0.07
    Activations Density 0.067%

    No Known Activations