© 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. 56071
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with exponents and subscripts

    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
    æĸ°åĬłåĿ¡
    -0.10
    åĬłæĭ¿å¤§
    -0.09
    /-
    -0.07
    nek
    -0.06
    ä¸Ģ个æĺ¯
    -0.06
    idaan
    -0.05
    tedy
    -0.05
    -
    -0.05
    \-
    -0.05
    èĭijå°ıåĮº
    -0.05
    POSITIVE LOGITS
    两ä¸į误
    0.09
    culares
    0.08
    önh
    0.08
     Trinh
    0.08
    æĹıèĩªæ²»åİ¿
    0.08
    -fw
    0.08
     következ
    0.08
    گز
    0.08
    timi
    0.08
    à¹Īะ
    0.08
    Activations Density 0.022%

    No Known Activations