© 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. 8044
    Prev
    Next
    INDEX
    Explanations

    panels

    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
    volve
    -0.08
    oges
    -0.08
    ogo
    -0.08
     Höh
    -0.08
    å¾Ĺèµ·
    -0.07
    باÙĩ
    -0.07
     пÑĢиÑģ
    -0.07
    ogg
    -0.07
    ably
    -0.07
    ucas
    -0.07
    POSITIVE LOGITS
    ç¡®ä¿Ŀ
    0.09
     ensures
    0.09
    æľīåĬ©äºİ
    0.08
    使å¾Ĺ
    0.08
    使ä»ĸ
    0.08
    使
    0.08
    確ä¿Ŀ
    0.08
     giúp
    0.08
    è¿Ļæł·åı¯ä»¥
    0.07
    ç¡®ä¿Ŀå®īåħ¨
    0.07
    Activations Density 0.277%

    No Known Activations