© 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. 40586
    Prev
    Next
    INDEX
    Explanations

    list manipulation with join or split

    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
     Abbott
    -0.07
    ewart
    -0.07
    ille
    -0.06
    ÅĤasz
    -0.06
     [('
    -0.06
    atil
    -0.06
    hre
    -0.06
    itan
    -0.06
     wise
    -0.06
    临走
    -0.06
    POSITIVE LOGITS
    맥
    0.09
    isir
    0.08
     Wib
    0.08
    åĨįæľī
    0.08
    è·Łäºº
    0.07
    æĻĵ举
    0.07
    æĺ¥æĿ¥
    0.07
    ÑĢиз
    0.07
    kse
    0.07
    viste
    0.07
    Activations Density 0.094%

    No Known Activations