© 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. 38899
    Prev
    Next
    INDEX
    Explanations

    above, link, right

    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
    swick
    -0.10
    主è¦ģç»ıèIJ¥
    -0.08
    è¿Ļ个è§Ĵèī²
    -0.07
    kala
    -0.07
    رسÛĮ
    -0.07
    ëĵľë¦¬
    -0.07
    è¿Ļ个æĸ¹æ³ķ
    -0.07
    äºĨè¿Ļ个
    -0.07
     (!((
    -0.07
    è¿Ļ个è¯į
    -0.07
    POSITIVE LOGITS
    æīĢè¿°
    0.10
    æīĢ示
    0.09
    æīĢè¿°çļĦ
    0.08
     notwithstanding
    0.08
     above
    0.07
    è¿°
    0.07
    æīĢåĪĹ
    0.07
    above
    0.07
    駿
    0.07
     rév
    0.07
    Activations Density 0.100%

    No Known Activations