© 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. 58321
    Prev
    Next
    INDEX
    Explanations

    neglecting or dismissing variables

    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
    uvi
    -0.08
    शि
    -0.07
    hini
    -0.07
    åıĸèĢĮ代ä¹ĭ
    -0.07
     Stell
    -0.07
    é«ĺ人
    -0.07
    并éĿŀæĺ¯
    -0.07
    ׼×ķף
    -0.07
    heb
    -0.07
    åİŁåĪĽ
    -0.07
    POSITIVE LOGITS
     irrelevant
    0.10
     negligible
    0.10
    ä¸įåıĤä¸İ
    0.09
    æĹłåħ³
    0.09
    ä¸įéĩįè¦ģ
    0.09
    ä¸įå½±åĵį
    0.08
    æĪij们ä¸į
    0.08
    ä¸įæī¿æĭħ
    0.08
     insignificant
    0.07
    ä¸įæĸ¹ä¾¿
    0.07
    Activations Density 0.035%

    No Known Activations