© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    easier to

    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
    æĹ¢æľī
    -0.07
    urier
    -0.06
    .localization
    -0.06
    æł¼å°Ķ
    -0.06
    oloc
    -0.06
    bm
    -0.06
    ä¸´æ±Ł
    -0.06
    emand
    -0.06
    IGA
    -0.06
     Cuc
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.25
    åľ¨è¿Ļç§į
    0.21
    è¿ĻæŶ
    0.20
    åľ¨æѤ
    0.20
    æѤæŶ
    0.20
    è¿ĻæŶåĢĻ
    0.19
    åľ¨è¿Ļ个æŶåĢĻ
    0.19
    æѤæŶçļĦ
    0.19
    åľ¨è¿Ļä¸Ģ
    0.18
    åľ¨è¿ĻéĩĮ
    0.18
    Activations Density 0.272%

    No Known Activations