© 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. 21515
    Prev
    Next
    INDEX
    Explanations

    class Migration

    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
    ortable
    -0.07
    avais
    -0.07
    产åĵģç±»åŀĭ
    -0.07
    Ỽm
    -0.07
    erts
    -0.07
    simd
    -0.07
     Seymour
    -0.07
    ÐļÑĥпиÑĤÑĮ
    -0.07
    Regs
    -0.07
    çİĭçİī
    -0.07
    POSITIVE LOGITS
    icola
    0.07
    ÅĽcie
    0.07
    éļİ
    0.07
    éĴĪ对
    0.07
    elé
    0.07
    YO
    0.06
    idi
    0.06
    代çłģ
    0.06
    代çłģå¦Ĥä¸ĭ
    0.06
     ðŁij
    0.06
    Activations Density 0.002%

    No Known Activations