© 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. 8673
    Prev
    Next
    INDEX
    Explanations

    regex syntax

    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
    -bot
    -0.07
    ç§ĴéĴŁ
    -0.07
    axter
    -0.07
    äºĨåįĬ天
    -0.07
    weiler
    -0.07
    lina
    -0.06
    onom
    -0.06
    abbit
    -0.06
    æĸ¯é¡¿
    -0.06
    æ¸Ĭ
    -0.06
    POSITIVE LOGITS
    ä¸įéĹ®
    0.07
    说åĪ°åºķ
    0.07
    å¤ļæł·çļĦ
    0.07
    å°¤åħ¶æĺ¯
    0.07
    idos
    0.07
    çī¹åĪ«æĺ¯
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    اÙĤ
    0.06
    Globals
    0.06
    èĦ±é¢ĸ
    0.06
    Activations Density 0.022%

    No Known Activations