© 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. 38865
    Prev
    Next
    INDEX
    Explanations

    used for applications or components

    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
    æīĢæľīçļĦ
    -0.08
    æīĢæľīè¿ĻäºĽ
    -0.08
    åIJĮä¸Ĭ
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.08
    ä»»ä½ķäºĭæĥħ
    -0.07
    åħ¨éĥ¨çļĦ
    -0.07
     absolutamente
    -0.07
    nton
    -0.07
     aforementioned
    -0.07
     absolument
    -0.07
    POSITIVE LOGITS
     ___
    0.12
     ____
    0.11
     ______
    0.11
    ____
    0.11
     _____
    0.11
     __
    0.10
    ________
    0.10
    ＿＿
    0.10
    _____
    0.09
     ________
    0.09
    Activations Density 0.302%

    No Known Activations