© 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. 33412
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation/operators

    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
    ¿
    -0.09
    pruch
    -0.08
    alak
    -0.08
    اعة
    -0.08
    colo
    -0.08
    lify
    -0.08
    ÅĤac
    -0.08
    æĽľæĹ¥
    -0.08
    ़
    -0.08
    lat
    -0.08
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.07
    imes
    0.07
    hydr
    0.06
    uert
    0.06
     anus
    0.06
    uai
    0.06
    moid
    0.06
    ua
    0.06
    ro
    0.06
    éĿ©
    0.06
    Activations Density 0.112%

    No Known Activations