© 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. 29837
    Prev
    Next
    INDEX
    Explanations

    mathematical "Let" statements

    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
    endor
    -0.07
    ynn
    -0.06
    馨
    -0.06
    elper
    -0.06
    uyan
    -0.06
    alem
    -0.06
    ccion
    -0.06
    ulate
    -0.06
    æ²Ľ
    -0.06
     Hoff
    -0.06
    POSITIVE LOGITS
    zzo
    0.08
    luk
    0.08
    зой
    0.07
    zzi
    0.07
    ÙĬÙĪÙĨ
    0.07
    ä¸ĥåįģäºĮ
    0.07
    cios
    0.07
     Zav
    0.07
    ESE
    0.07
    bens
    0.06
    Activations Density 0.006%

    No Known Activations