© 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. 40210
    Prev
    Next
    INDEX
    Explanations

    majority requirements

    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
    asca
    -0.09
    _ctl
    -0.08
    serter
    -0.08
    ()['
    -0.08
    ikos
    -0.08
     terecht
    -0.08
     Trotzdem
    -0.08
    vido
    -0.08
    æĮºå¥½çļĦ
    -0.07
    wak
    -0.07
    POSITIVE LOGITS
    æīįè¡Į
    0.11
     preferably
    0.09
     ideally
    0.08
     AND
    0.08
    èĩ³å°ij
    0.08
    æĸ¹åı¯
    0.08
    æīįæľīåı¯èĥ½
    0.08
    ä¹Łå°±æĺ¯
    0.08
    æį¢åı¥è¯Ŀ说
    0.08
    åIJĮæŶè¿ĺè¦ģ
    0.08
    Activations Density 0.023%

    No Known Activations