© 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. 12276
    Prev
    Next
    INDEX
    Explanations

    bound, associated, conjugated, binding

    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
    èķ
    -0.07
    åįĥæĸ¤
    -0.07
    _increment
    -0.07
     unilateral
    -0.07
    è£ģ
    -0.07
    è£ĺ
    -0.06
    areth
    -0.06
    baugh
    -0.06
    竺
    -0.06
    æ±ĩèģļ
    -0.06
    POSITIVE LOGITS
    çĬ¶æĢģçļĦ
    0.09
     depot
    0.09
    æĿŁç¼ļ
    0.09
    ä¸į解
    0.08
    ç´§å¯Ĩç»ĵåIJĪ
    0.08
    /embed
    0.08
    çļĦçĭĢæħĭ
    0.08
     ÑħÑĢанение
    0.08
    游离
    0.08
     tightly
    0.08
    Activations Density 0.099%

    No Known Activations