© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50255
    Prev
    Next
    INDEX
    Explanations

    rights and duties

    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
     mire
    -0.09
    åıįåĢĴæĺ¯
    -0.08
    ä¸įåı¯æĢķ
    -0.08
    elio
    -0.07
    Į¨
    -0.07
    è¨Ģè¡Į
    -0.07
    æīĵèµ·
    -0.07
    æĻ¦
    -0.07
    èĩªå¸¦
    -0.07
    å¦Ĥçİī
    -0.07
    POSITIVE LOGITS
     principle
    0.08
    å®ģæĦ¿
    0.08
    æİ¢
    0.07
     principe
    0.07
    æĽ´éĩįè¦ģ
    0.07
    å²Ĥ
    0.07
    lec
    0.07
    ứa
    0.07
    æĽ´å¼º
    0.07
     outweigh
    0.07
    Activations Density 0.110%

    No Known Activations