© 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. 43954
    Prev
    Next
    INDEX
    Explanations

    Hall cell

    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
    gues
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
    天éķ¿
    -0.07
     اÙĦÙĪاØŃد
    -0.07
    поÑĢ
    -0.06
    æŶéĹ´çŁŃ
    -0.06
    ended
    -0.06
    gent
    -0.06
    ä¸Ģ身
    -0.06
    ontan
    -0.06
    POSITIVE LOGITS
     locus
    0.09
     геомеÑĤÑĢи
    0.08
    æĺ¯ä¸ĢæĿ¡
    0.07
    è©
    0.07
    обÑĢаз
    0.07
    åł´æīĢãģ¯
    0.07
     setC
    0.07
    éĻIJå®ļ
    0.07
    æĪijå¦Ī
    0.07
    符åIJĪæĿ¡ä»¶
    0.07
    Activations Density 0.003%

    No Known Activations