© 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. 8573
    Prev
    Next
    INDEX
    Explanations

    difference

    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
    èĢĮä¸įæĺ¯
    -0.07
    çĥŃçĤ¹
    -0.07
    idor
    -0.07
    ext
    -0.07
    aint
    -0.07
    lass
    -0.07
    escu
    -0.07
    缸æ¯Ķäºİ
    -0.06
    ä¸įåIJĮäºİ
    -0.06
    ä¸įåĥı
    -0.06
    POSITIVE LOGITS
    å·®å¼Ĥ
    0.14
    çļĦå·®å¼Ĥ
    0.13
     differences
    0.13
    å·®åĪ«
    0.12
    çĽ¸å·®
    0.12
     difference
    0.12
    ä¹ĭåĪ«
    0.11
     perbedaan
    0.11
    åIJĦèĩªçļĦ
    0.11
     Differences
    0.11
    Activations Density 0.045%

    No Known Activations