© 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. 13986
    Prev
    Next
    INDEX
    Explanations

    references and bibliographies

    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
    æĪIJ人
    -0.07
    lev
    -0.07
    ORN
    -0.07
    axes
    -0.07
    éĵ®
    -0.07
    æĹłæīĢ
    -0.07
    ORY
    -0.07
    æĸ°å¤©åľ°
    -0.07
    .fx
    -0.07
    QL
    -0.07
    POSITIVE LOGITS
    misc
    0.07
    ansir
    0.07
    bur
    0.07
    _PARSE
    0.07
    dam
    0.07
     trak
    0.06
    vik
    0.06
     mom
    0.06
    æ¶Īæļij
    0.06
     Mom
    0.06
    Activations Density 0.218%

    No Known Activations