© 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. 57397
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
     Suomi
    -0.07
    atham
    -0.07
    åħ¬åħ±åľºæīĢ
    -0.07
    åѦåı²
    -0.07
    agh
    -0.07
     Rough
    -0.07
    agus
    -0.07
    ä¸įåİ»
    -0.06
    /gcc
    -0.06
    /features
    -0.06
    POSITIVE LOGITS
    积
    0.07
    é«ĺäºİ
    0.07
     probabilities
    0.07
     possibil
    0.07
    prob
    0.07
    FileStream
    0.06
    æīĢæľī
    0.06
    _INF
    0.06
     Prob
    0.06
    å¾ĹçĽĬ
    0.06
    Activations Density 0.007%

    No Known Activations