© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49974
    Prev
    Next
    INDEX
    Explanations

    xml doctype and metadata

    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
    agus
    -0.06
    aped
    -0.06
    гин
    -0.06
    æij¸æ¸ħ
    -0.06
    å¼łçİī
    -0.06
    éĢīæĿIJ
    -0.06
     rowspan
    -0.06
    åı²
    -0.06
    çĽij
    -0.06
    POSITIVE LOGITS
    ims
    0.08
    ÑĢма
    0.07
    htable
    0.07
    åĩºæĿ¥çļĦ
    0.07
    interop
    0.07
     reprises
    0.07
    \Bundle
    0.07
     Bres
    0.07
    è¿Ľä¸ĢæŃ¥æ·±åĮĸ
    0.07
    jec
    0.07
    Activations Density 1.194%

    No Known Activations