© 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. 13812
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical terms

    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
     Weinstein
    -0.08
    æıIJè¦ģ
    -0.07
    ä¸ĬåįĬ
    -0.06
    éĵ¸
    -0.06
    åı·ä»¤
    -0.06
    屡
    -0.06
     ho
    -0.06
    åŁĤ
    -0.06
    åIJ¼
    -0.06
    nat
    -0.06
    POSITIVE LOGITS
    æĸ¯é¡¿
    0.09
    ×ķ×ĵ×Ķ
    0.09
    _stdout
    0.08
    é»ij马
    0.08
    éĺ²å¯Ĵ
    0.08
    åı¯èĥ½åŃĺåľ¨
    0.07
    ictory
    0.07
    STD
    0.07
    åĨįä¸Ģ次
    0.07
    umsi
    0.07
    Activations Density 0.003%

    No Known Activations