© 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. 45847
    Prev
    Next
    INDEX
    Explanations

    uncommon, increase, or disruption

    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
    è¡·å¿ĥçļĦ
    -0.07
    åĴĮæĪijçļĦ
    -0.07
     ifndef
    -0.07
    ,:),
    -0.07
     Piso
    -0.07
     Musta
    -0.07
    ạn
    -0.07
    ä¸ĭåIJĮ
    -0.07
     downstairs
    -0.06
    æĪij为
    -0.06
    POSITIVE LOGITS
     reportedly
    0.14
     [
    0.11
     “[
    0.10
    [
    0.10
     ([
    0.10
    (http
    0.10
     )[
    0.09
    '[
    0.09
    ,[
    0.09
     http
    0.09
    Activations Density 1.496%

    No Known Activations