© 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. 18940
    Prev
    Next
    INDEX
    Explanations

    alternating rows

    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
    å§Ĩæĸ¯
    -0.09
    æĹłåı¯
    -0.07
    rim
    -0.07
    å¼ĢåѦ第ä¸Ģ课
    -0.07
    ãĤ¹ãĥ¡
    -0.07
     unw
    -0.07
    untu
    -0.07
    PT
    -0.07
    ully
    -0.07
    enso
    -0.06
    POSITIVE LOGITS
    acher
    0.07
    çijŀ
    0.07
    好
    0.07
    [++
    0.07
    äº¤æĽ¿
    0.07
    ishops
    0.06
     Stich
    0.06
    acific
    0.06
    ç½
    0.06
    ifting
    0.06
    Activations Density 0.001%

    No Known Activations