© 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. 44044
    Prev
    Next
    INDEX
    Explanations

    data structure syntax

    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
    avig
    -0.07
     übern
    -0.07
    å¤ļè¾¾
    -0.07
    广大çļĦ
    -0.07
    æĪijä¸įç¦ģ
    -0.07
     Piot
    -0.07
    nowled
    -0.07
    ç»Ļ对æĸ¹
    -0.06
    Ø«ÙĬر
    -0.06
    uos
    -0.06
    POSITIVE LOGITS
    大æĶ¾
    0.07
    è¿Ļæĺ¯æĪijçļĦ
    0.07
    enson
    0.07
    gos
    0.07
    åIJĮæľŁ
    0.07
    dze
    0.07
    mainen
    0.07
    .IsActive
    0.07
    aza
    0.07
    ضÙĦ
    0.06
    Activations Density 0.020%

    No Known Activations