© 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. 12169
    Prev
    Next
    INDEX
    Explanations

    RelativeLayout xmlns

    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
    er
    -0.12
    lessly
    -0.11
    ////////////////////////////////////////////////////////
    -0.10
    naires
    -0.09
    -quarters
    -0.09
    eri
    -0.09
    ////////////
    -0.09
    zinho
    -0.08
    spiel
    -0.08
     tslint
    -0.08
    POSITIVE LOGITS
    Ø©
    0.15
    ãģĺãĤģãģ¦
    0.10
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.09
    ation
    0.09
    zelfde
    0.09
    ãģ£ãģįãĤĬ
    0.09
    oretical
    0.09
    Ùijا
    0.08
    ãģ¦
    0.08
    cules
    0.08
    Activations Density 1.395%

    No Known Activations