© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30329
    Prev
    Next
    INDEX
    Explanations

    special blocks and formatting

    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
    çĻ½è¡£
    -0.07
    æ±İ
    -0.07
    壮
    -0.07
    ajari
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    arsing
    -0.07
    Ư
    -0.07
     اÙĦÙħÙĦÙĥ
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
     abd
    -0.06
    POSITIVE LOGITS
     subsection
    0.08
    fy
    0.07
    subsection
    0.06
    indent
    0.06
    åIJ¬åıĸäºĨ
    0.06
    enced
    0.06
    ä¾ĽåºĶ产åĵģ
    0.06
    ìĪł
    0.06
    æĪĸåĪłéĻ¤
    0.06
     pá
    0.06
    Activations Density 0.193%

    No Known Activations