© 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. 60695
    Prev
    Next
    INDEX
    Explanations

    choose arc

    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
    ÙĪØ´
    -0.09
    èĩªå·±çļĦ梦æĥ³
    -0.08
    anaan
    -0.08
    麻éĽĢ
    -0.08
    ÐľÐ¡
    -0.08
     Patr
    -0.08
    uzzi
    -0.08
    ä¸īå®Ŀ
    -0.08
    [random
    -0.08
    rawn
    -0.08
    POSITIVE LOGITS
     continuity
    0.09
     quadrant
    0.07
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.07
     contexts
    0.07
     sign
    0.07
    Runtime
    0.06
    _choose
    0.06
    æĭ¾
    0.06
    .choose
    0.06
    è¿ŀç»ŃæĢ§
    0.06
    Activations Density 0.005%

    No Known Activations