© 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. 41034
    Prev
    Next
    INDEX
    Explanations

    Exercise Italic Weld

    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
    enne
    -0.08
    मित
    -0.08
    Ñĩиков
    -0.08
    aru
    -0.07
    gia
    -0.07
    @show
    -0.07
    å¾Ĺæ°´
    -0.07
    ä¸ŃæĭĽ
    -0.07
    colo
    -0.07
    Ñĩик
    -0.07
    POSITIVE LOGITS
    mime
    0.08
    çľĭåľ¨
    0.06
    æ¯Ľ
    0.06
     magn
    0.06
    lis
    0.06
    åģļ大
    0.06
    åIJIJ
    0.06
    åıijå±ķè¶ĭåĬ¿
    0.06
    ulk
    0.06
    o
    0.06
    Activations Density 0.042%

    No Known Activations