© 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. 40073
    Prev
    Next
    INDEX
    Explanations

    concerned users or interests

    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
    ä¸Ĭè¯īäºİ
    -0.07
    ock
    -0.07
    stdout
    -0.07
    ajn
    -0.06
    aget
    -0.06
    主è¦ģåİŁåĽłæĺ¯
    -0.06
     Tats
    -0.06
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    -0.06
    èĪµ
    -0.06
    åıªèĥ½è¯´
    -0.06
    POSITIVE LOGITS
     bersangkutan
    0.13
     concerned
    0.08
    øy
    0.08
    è¯¥é¡¹çĽ®
    0.07
    ustos
    0.07
    ãģĿãģ®
    0.07
     respectiv
    0.07
    enhagen
    0.07
    stood
    0.07
    idden
    0.07
    Activations Density 0.247%

    No Known Activations