© 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. 34470
    Prev
    Next
    INDEX
    Explanations

    COPY FROM

    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
    forge
    -0.08
    berry
    -0.07
    åħ¶éģĵ
    -0.07
     Previd
    -0.07
    sd
    -0.07
    izer
    -0.07
     collector
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    ichier
    -0.07
    ptime
    -0.06
    POSITIVE LOGITS
    åľ¨åħ¶ä¸Ń
    0.14
     darin
    0.13
     therein
    0.13
    æĶ¾è¿Ľåİ»
    0.12
    ä¸İä¹ĭ
    0.12
     ÑĤÑĥда
    0.12
    ãģĿãģĵãģ«
    0.11
     nela
    0.11
     оÑĤÑĤ
    0.11
     dort
    0.11
    Activations Density 0.396%

    No Known Activations