© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    shooter or shoot

    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
    ìį¨
    -0.11
    strup
    -0.10
    sworth
    -0.09
    ì§ĵ
    -0.09
    umente
    -0.09
    zzi
    -0.09
    -esque
    -0.09
    iless
    -0.09
    ÅĽc
    -0.09
    ÃŃss
    -0.08
    POSITIVE LOGITS
    аем
    0.10
    enticate
    0.08
    ات
    0.08
    a
    0.08
    ами
    0.08
    ing
    0.07
    ا
    0.07
    (sh
    0.07
    mallow
    0.07
    ses
    0.07
    Activations Density 0.001%

    No Known Activations