© 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. 9815
    Prev
    Next
    INDEX
    Explanations

    HTML rows and table cells

    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
    Defs
    -0.08
    system
    -0.08
    subpackage
    -0.08
     fleets
    -0.07
    ron
    -0.07
    ç³»ç»ŁçŃī
    -0.07
    cini
    -0.07
    rts
    -0.07
    ä½ĵç³»çļĦ
    -0.07
    imeo
    -0.07
    POSITIVE LOGITS
    éĻ¤
    0.08
     komplett
    0.07
     ÑģоÑģÑĤав
    0.07
     composto
    0.07
    æĿ¡
    0.07
    _except
    0.06
    åħ¨ä½ĵæĪIJåijĺ
    0.06
     íĮ¨íĦ´
    0.06
    åīįåįĬ
    0.06
     pattern
    0.06
    Activations Density 0.016%

    No Known Activations