© 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. 62254
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
    Å«k
    -0.07
    Ý
    -0.07
    tering
    -0.07
    mailer
    -0.07
     Comer
    -0.07
    SqlCommand
    -0.06
    colo
    -0.06
    åı¤æĢª
    -0.06
    :update
    -0.06
    usiness
    -0.06
    POSITIVE LOGITS
    ogen
    0.08
    è½½åħ¥
    0.07
    edig
    0.07
    weiler
    0.07
     Named
    0.07
    ä¸Ģå¸Ĩ
    0.07
    èķĥ
    0.06
    .nom
    0.06
    åĽ¢
    0.06
    osl
    0.06
    Activations Density 0.002%

    No Known Activations