© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific notation

    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
    iple
    -0.07
    olen
    -0.07
     atl
    -0.07
    éĻ¤äºĨè¦ģ
    -0.07
     Eag
    -0.07
    éĻ¤äºĨæľī
    -0.07
    KHR
    -0.07
    èĢģå¸Ī们çļĦ
    -0.07
     unknow
    -0.06
    çļĦèĢģå¸Ī
    -0.06
    POSITIVE LOGITS
    ä¸Ģçķª
    0.07
    çĶļèĢħ
    0.07
    soever
    0.07
    çĶļ
    0.07
    shelf
    0.06
    craft
    0.06
    raq
    0.06
    каÑģ
    0.06
    রà§įব
    0.06
     craft
    0.06
    Activations Density 0.007%

    No Known Activations