© 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. 38917
    Prev
    Next
    INDEX
    Explanations

    "Field"

    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
    à¸Īัà¸ĩ
    -0.07
    ä¸ĩéĩĮ
    -0.07
    个åĽŀçŃĶ
    -0.07
    otti
    -0.06
    ambul
    -0.06
    çĭ¬ç«ĭçļĦ
    -0.06
    ç«ĭå¾·
    -0.06
    åIJĪéĢĤ
    -0.06
    zig
    -0.06
    è¦ģæ±Ĥåľ¨
    -0.06
    POSITIVE LOGITS
    è¿Ľè¡Įæ¯Ķè¾ĥ
    0.11
    缸æ¯Ķè¾ĥ
    0.10
     comparison
    0.10
    ä¸įå¦Ĥ
    0.10
    Comparison
    0.10
    æ¯Ķä¸įä¸Ĭ
    0.09
     worse
    0.09
    compare
    0.09
     comparer
    0.09
     Compare
    0.09
    Activations Density 0.003%

    No Known Activations