© 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. 49191
    Prev
    Next
    INDEX
    Explanations

    because of, would like, want to

    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
    æĬ¢çľ¼
    -0.07
    laud
    -0.07
    ä¸Ģç³»åĪĹçļĦ
    -0.07
    ugins
    -0.07
    ptest
    -0.07
     procur
    -0.07
    è´ºåį¡
    -0.07
     Certif
    -0.06
    ács
    -0.06
    åķĬ
    -0.06
    POSITIVE LOGITS
     magari
    0.07
    èĢĮæĺĵ
    0.06
    aver
    0.06
    å½¢ãģ§
    0.06
    åįĬåĬŁ
    0.06
    ër
    0.06
    åt
    0.06
    weis
    0.06
    ä¸ī两
    0.06
    atas
    0.06
    Activations Density 0.020%

    No Known Activations