© 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. 37956
    Prev
    Next
    INDEX
    Explanations

    broader context / scope

    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
    Hotline
    -0.08
    chnik
    -0.07
    æĥŁæľī
    -0.07
    orman
    -0.07
     einzelnen
    -0.07
    主è¦ģç»ıèIJ¥
    -0.07
    luv
    -0.07
    åĪ¹éĤ£éĹ´
    -0.07
    বা
    -0.07
    çªģå¦Ĥåħ¶
    -0.07
    POSITIVE LOGITS
    æĽ´å¹¿
    0.10
    /global
    0.09
    æĽ´å¤§çļĦ
    0.09
     broader
    0.09
     encompass
    0.09
    Than
    0.08
     beyond
    0.08
    _than
    0.08
     Beyond
    0.08
    /general
    0.08
    Activations Density 0.022%

    No Known Activations