© 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. 24473
    Prev
    Next
    INDEX
    Explanations

    why questions for emphasis

    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
    PageIndex
    -0.09
    uset
    -0.07
    è·¯åĴĮ
    -0.07
    åĸĩ
    -0.07
    ources
    -0.07
    Millis
    -0.07
    *out
    -0.07
     stok
    -0.07
    åĩłä¸ĩ
    -0.07
    agram
    -0.07
    POSITIVE LOGITS
    æĻļæĬ¥
    0.07
    ç«¥åŃIJ
    0.07
     [
    0.07
    æĸ°ä¸ľæĸ¹
    0.06
    大çİĭ
    0.06
    ioni
    0.06
    èĩªåįij
    0.06
     beliau
    0.06
    ä¼Łå¤§
    0.06
    以大
    0.06
    Activations Density 0.014%

    No Known Activations