© 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. 20116
    Prev
    Next
    INDEX
    Explanations

    every time

    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
    èĢĮä»ĸ
    -0.08
     dÃłn
    -0.07
     himself
    -0.07
    èĢĮæѤæŶ
    -0.07
     herself
    -0.07
    es
    -0.07
    ropol
    -0.07
    åľ¨ä»ĸçľĭæĿ¥
    -0.07
    rell
    -0.07
    ะ
    -0.06
    POSITIVE LOGITS
     you
    0.10
    /how
    0.10
     someone
    0.10
     they
    0.09
    人们
    0.09
     it
    0.09
     we
    0.08
    indi
    0.08
    /if
    0.08
    abouts
    0.07
    Activations Density 0.101%

    No Known Activations