© 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. 20986
    Prev
    Next
    INDEX
    Explanations

    key, cored, canal, history, brakes, schemes, teens, Explorer

    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
    ComputedStyle
    -0.08
    gire
    -0.08
    .documentation
    -0.08
    sait
    -0.07
    ATR
    -0.07
    ÉĻl
    -0.07
    Åijr
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    å®Įåħ¨ä¸į
    -0.07
     **^
    -0.07
    POSITIVE LOGITS
    çī¹çº§
    0.06
    Ùħص
    0.06
     conce
    0.06
    phas
    0.06
     Spl
    0.06
     Ced
    0.06
    审åĪ¤åijĺ
    0.06
    ä»Ļä¾ł
    0.06
    ibia
    0.06
    acia
    0.06
    Activations Density 0.767%

    No Known Activations