© 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. 24241
    Prev
    Next
    INDEX
    Explanations

    edit or update

    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
     desem
    -0.07
    綿
    -0.07
     createSelector
    -0.06
     Jacob
    -0.06
    åħŃåIJĪ
    -0.06
     crossed
    -0.06
    edin
    -0.06
    ersch
    -0.06
    -stack
    -0.06
     ford
    -0.06
    POSITIVE LOGITS
    (Edit
    0.12
     editing
    0.12
    /edit
    0.12
    (edit
    0.12
     Editing
    0.12
     edit
    0.11
     Edit
    0.11
    ç¼ĸè¾ij
    0.11
    Editing
    0.11
     ÑĢедакÑĤи
    0.11
    Activations Density 0.383%

    No Known Activations