© 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. 18793
    Prev
    Next
    INDEX
    Explanations

    end of line markers

    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
    otec
    -0.10
    ër
    -0.08
    åĽ¾æĸ¯
    -0.08
    æľªå¤®
    -0.08
     despe
    -0.08
    æ´¾åĩºæīĢæ°ijèѦ
    -0.08
    aner
    -0.08
    缸åħ³éĺħ读
    -0.08
    zol
    -0.08
    ansch
    -0.07
    POSITIVE LOGITS
    itz
    0.07
    hes
    0.06
    пи
    0.06
    ØŃØ©
    0.06
    PP
    0.06
    bur
    0.06
    beh
    0.06
    åľ¨åŃ¦ä¹łä¸Ĭ
    0.06
    è¿Ľåıĸ
    0.06
     Loch
    0.05
    Activations Density 0.007%

    No Known Activations