© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    approximation and accuracy

    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
    iedo
    -0.08
    iator
    -0.08
    idr
    -0.08
    å¼Ħ
    -0.07
     Colleg
    -0.07
    çľĭæĬ¤
    -0.07
    éĽ¯
    -0.07
    ieto
    -0.07
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.07
    价为
    -0.07
    POSITIVE LOGITS
     approximation
    0.09
    èĤīçľ¼
    0.08
    è¿ijä¼¼
    0.08
    è¶³å¤Ł
    0.08
     negligible
    0.08
    åı¯ä»¥æĶ¾å¿ĥ
    0.08
    ç¨ĭ度
    0.08
    误差
    0.07
    çļĦç¨ĭ度
    0.07
     approx
    0.07
    Activations Density 0.037%

    No Known Activations