© 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. 22140
    Prev
    Next
    INDEX
    Explanations

    excessively large or many

    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
    æĹłä¸Ģ
    -0.08
    çĭ¬ç«ĭçļĦ
    -0.08
    æĥŁä¸Ģ
    -0.08
    åı¯éĿłçļĦ
    -0.07
    å®Įæķ´çļĦ
    -0.07
    åĩºå£°
    -0.07
    温度为
    -0.07
    åĶ¯ä¸ĢçļĦ
    -0.07
    æľĢ好çļĦ
    -0.07
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.07
    POSITIVE LOGITS
    è¶³å¤Ł
    0.11
     relatively
    0.11
     sufficiently
    0.11
     excessively
    0.10
    è¾ĥ
    0.10
     unusually
    0.10
    éĩı大
    0.09
     extremely
    0.09
     large
    0.09
    è¼ĥ
    0.09
    Activations Density 0.237%

    No Known Activations