© 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. 32600
    Prev
    Next
    INDEX
    Explanations

    can't even X

    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
    µ¬
    -0.08
    %H
    -0.08
    æĹ¢
    -0.08
     именно
    -0.08
    åĩ¡äºĭ
    -0.08
    æ¨ĭ
    -0.08
    ä¹Łç¡®å®ŀ
    -0.08
    ä¹Łä¸įéĶĻ
    -0.08
    æĹ¢æľī
    -0.07
    åĪ«æĹł
    -0.07
    POSITIVE LOGITS
    ä½ķåĨµ
    0.13
    æĽ´åĪ«è¯´
    0.12
    æĽ´ä½ķåĨµ
    0.11
    ä½ķæ³ģ
    0.10
    ãģĻãĤī
    0.10
    æľĢåŁºæľ¬çļĦ
    0.10
     siquiera
    0.10
     sequer
    0.10
     even
    0.09
    ì¡°ì°¨
    0.09
    Activations Density 0.178%

    No Known Activations