© 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. 61196
    Prev
    Next
    INDEX
    Explanations

    webkit gradient

    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
    ำà¸Ļ
    -0.08
    èĩªå°ı
    -0.08
    nonnull
    -0.07
    avl
    -0.07
    :^(
    -0.07
    ÙİÙijÙĨ
    -0.07
    详æĥħ请
    -0.07
    -names
    -0.07
    PLO
    -0.07
    upiter
    -0.07
    POSITIVE LOGITS
    é¢ĺå¹²
    0.10
    ç¡®å®ŀæĺ¯
    0.08
    oc
    0.07
    è¿ĩæĿ¥
    0.07
    æľĢåIJİä¸Ģ个
    0.07
    座çļĦ
    0.07
     contrad
    0.06
    ä¸į管
    0.06
     ulang
    0.06
    æľ¬é¢ĺçŃĶæ¡Ī
    0.06
    Activations Density 0.002%

    No Known Activations