© 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. 41592
    Prev
    Next
    INDEX
    Explanations

    compose composition function

    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
    imei
    -0.07
    egers
    -0.07
    /if
    -0.07
    就好æ¯Ķ
    -0.07
    æģ¯
    -0.07
    essler
    -0.06
    é§Ħ
    -0.06
    знаÑĩа
    -0.06
    jar
    -0.06
    oretical
    -0.06
    POSITIVE LOGITS
    ี
    0.07
     вним
    0.07
    ìį¨
    0.07
    hoven
    0.07
    <![
    0.07
    çİ¥
    0.07
    otos
    0.07
    stown
    0.07
    nier
    0.07
     Potenza
    0.07
    Activations Density 0.001%

    No Known Activations