© 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. 16306
    Prev
    Next
    INDEX
    Explanations

    module definitions

    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
    igl
    -0.07
    夫æĸ¯åŁº
    -0.07
    ugal
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
     Kosten
    -0.06
    ype
    -0.06
    .jsp
    -0.06
    èĮĥæĸĩç½ij
    -0.06
    .hasOwnProperty
    -0.06
    opp
    -0.06
    POSITIVE LOGITS
    以ä¸ĬåĨħ容
    0.07
     cases
    0.07
    achs
    0.07
    åIJĦé¡¹å·¥ä½ľ
    0.07
    çļĦåºĶçĶ¨
    0.07
    çļĦå·¥ä½ľä¸Ń
    0.07
    澤
    0.07
    ново
    0.06
    足çIJĥåľº
    0.06
    alani
    0.06
    Activations Density 0.093%

    No Known Activations