© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    benchmark test

    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
    åįĬåľº
    -0.07
    ãģªãĤĤãģ®
    -0.06
    æĹ©æĻļ
    -0.06
    æĴŃ
    -0.06
    umann
    -0.06
     Lans
    -0.06
     kew
    -0.06
    enis
    -0.06
     respective
    -0.06
    å¹´ä¼ļ
    -0.06
    POSITIVE LOGITS
    ä¸İ客æĪ·
    0.07
    _ax
    0.07
     denial
    0.07
    rende
    0.07
    째
    0.07
     broken
    0.07
    YPD
    0.07
    çī¹æ´¾
    0.07
    _degree
    0.07
     Clause
    0.06
    Activations Density 0.048%

    No Known Activations