© 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. 61037
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Ïĩν
    -0.08
    INY
    -0.07
    èĻ½çĦ¶åľ¨
    -0.07
    çļĦé«ĺ端
    -0.07
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.07
     tanto
    -0.07
     Zut
    -0.06
    entai
    -0.06
    vla
    -0.06
    ÅĻenÃŃ
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.07
    说æĺ¯
    0.07
    vrier
    0.07
    enje
    0.07
     nanti
    0.07
     vice
    0.07
    亦çĦ¶
    0.07
    erb
    0.07
    ouri
    0.07
     sebaliknya
    0.07
    Activations Density 0.050%

    No Known Activations