© 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. 48722
    Prev
    Next
    INDEX
    Explanations

    a followed by common words

    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
    duct
    -0.08
    鸳
    -0.08
    ãģĽãģĦ
    -0.07
    .RunWith
    -0.07
    妥妥
    -0.07
    çļĦæĪij们
    -0.07
    æį¢æĿ¥çļĦ
    -0.07
    ãĥ«ãĥ¼ãĥł
    -0.07
    èIJ¥éĢłèī¯å¥½
    -0.07
    piler
    -0.07
    POSITIVE LOGITS
    oretical
    0.07
    ipan
    0.07
    éĩ
    0.07
    YPE
    0.07
    áºŃp
    0.07
    resi
    0.06
    avan
    0.06
    <u
    0.06
    agian
    0.06
    好人
    0.06
    Activations Density 0.102%

    No Known Activations