© 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. 24610
    Prev
    Next
    INDEX
    Explanations

    reasons for events

    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
    ä¸Ĭä¸ĢæĿ¡
    -0.08
    ä½ĨéĤ£
    -0.07
    缸ä¾Ŀ
    -0.07
    ä½Ĩæĺ¯ä¸Ģ
    -0.07
    atz
    -0.07
    /update
    -0.07
    .fail
    -0.06
    ÑĪед
    -0.06
    ]{
    -0.06
    ictures
    -0.06
    POSITIVE LOGITS
     due
    0.11
    åĽłä¸º
    0.10
     thanks
    0.10
    due
    0.10
    åĽłä¸ºæľī
    0.10
     owing
    0.09
     благодаÑĢÑı
    0.09
     because
    0.09
    because
    0.09
    thanks
    0.09
    Activations Density 0.021%

    No Known Activations