© 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. 34413
    Prev
    Next
    INDEX
    Explanations

    attribute keys and values

    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
    {@
    -0.07
    èĻ½çĦ¶
    -0.07
    Interpolator
    -0.07
     ((_
    -0.07
    enni
    -0.07
    (that
    -0.06
    ifter
    -0.06
    ä¼ļè®®çĶ±
    -0.06
    _INTEGER
    -0.06
    creen
    -0.06
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.07
    ublic
    0.07
    è½¼
    0.07
    /up
    0.07
    åĬªåĬĽå®ŀçİ°
    0.07
    éģĵæĿ¥
    0.07
    dbl
    0.07
    æĹ¥åIJij
    0.07
    -fast
    0.07
    ¹Ħ
    0.07
    Activations Density 0.003%

    No Known Activations