© 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. 55829
    Prev
    Next
    INDEX
    Explanations

    constant and index

    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
    ros
    -0.06
    ika
    -0.06
    å¦Ĩ
    -0.06
    -0.06
     Flour
    -0.05
     pav
    -0.05
    _cum
    -0.05
    æµĵ度为
    -0.05
    çļĸ
    -0.05
    -
    -0.05
    POSITIVE LOGITS
    ä¹ŁåĽł
    0.09
    ä¸ĭåĬŁå¤«
    0.09
    ä»İèĢĮæıIJé«ĺ
    0.09
    å¿«æĬ¥
    0.09
    çĪĽ
    0.08
    å®ĺæĸ¹åįļ客
    0.08
    æıīäºĨ
    0.08
    chedulers
    0.08
    ulti
    0.08
    èĢĮåħ¥
    0.08
    Activations Density 0.007%

    No Known Activations