© 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. 61451
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    isel
    -0.08
     nhá»ĭn
    -0.07
    纨
    -0.07
    /rc
    -0.07
    gabe
    -0.07
    çŃ¾
    -0.07
    raz
    -0.07
    rc
    -0.07
    доми
    -0.06
    бла
    -0.06
    POSITIVE LOGITS
    onter
    0.07
    é©Ĺ
    0.07
     Usai
    0.06
    .serial
    0.06
    åįĩ
    0.06
    éĸ
    0.06
    cheme
    0.06
    wali
    0.06
    ervised
    0.06
    év
    0.06
    Activations Density 0.103%

    No Known Activations