© 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. 65518
    Prev
    Next
    INDEX
    Explanations

    sequence of letters and numbers

    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
    uc
    -0.07
    plats
    -0.07
    åĩºä¸į
    -0.07
    кло
    -0.06
    md
    -0.06
     fucking
    -0.06
    两个æĸ¹éĿ¢
    -0.06
    uger
    -0.06
    ijan
    -0.06
    æĺ¯è¢«
    -0.06
    POSITIVE LOGITS
    èľ»
    0.08
    ¿
    0.08
    sse
    0.07
     voc
    0.07
    OrFail
    0.07
     Ultim
    0.07
    ÙĨÛĮÙĨ
    0.07
     seped
    0.07
    ramento
    0.07
    stw
    0.07
    Activations Density 0.028%

    No Known Activations