© 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. 41210
    Prev
    Next
    INDEX
    Explanations

    . Branch, $, function

    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
    æĹ¥æ´»åĬ¨
    -0.07
    æĭīå¾·
    -0.07
    erdo
    -0.07
    é¡¹çĽ®çļĦ建设
    -0.07
    èIJĿèİī
    -0.07
    ,:,:
    -0.07
    ارد
    -0.07
     Festiv
    -0.07
    袴
    -0.07
    åįĥèIJ¬
    -0.07
    POSITIVE LOGITS
    age
    0.07
    esy
    0.07
    ampa
    0.06
     пÑĢока
    0.06
     Lamp
    0.06
     Moor
    0.06
    ìĿ´íĬ¸
    0.06
    å¾ĢéĩĮ
    0.06
    éĩijå±±
    0.06
    é¾Ļçıł
    0.06
    Activations Density 1.349%

    No Known Activations