© 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. 22155
    Prev
    Next
    INDEX
    Explanations

    sqrt(

    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
    olest
    -0.07
    vr
    -0.06
     ratio
    -0.06
    umere
    -0.06
    è¡¡
    -0.06
    ä¸ĥåįģäºĮ
    -0.06
     Ratio
    -0.06
    uter
    -0.06
     denominator
    -0.06
    हाà¤Ĥ
    -0.06
    POSITIVE LOGITS
    æ»ļ
    0.08
    翻天
    0.07
    ensi
    0.07
    aglio
    0.07
    à¸ģะ
    0.07
    èIJ¤çģ«
    0.07
    bev
    0.07
    ÏĢη
    0.07
    лÑĥб
    0.07
    rup
    0.07
    Activations Density 0.031%

    No Known Activations