© 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. 11469
    Prev
    Next
    INDEX
    Explanations

    stellar branches or curves

    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
    ç¿ģ
    -0.07
    ebro
    -0.07
     queued
    -0.07
    ãĤ«ãĤ¦ãĥ³
    -0.07
    æĪĸå°ij
    -0.07
    漫
    -0.06
    å®ļåIJij
    -0.06
    BITS
    -0.06
    ryp
    -0.06
    AAD
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸ĢæĿ¡
    0.11
     curves
    0.10
    æĽ²çº¿çļĦ
    0.10
     curve
    0.10
    è¿ĻæĿ¡
    0.09
    æĽ²çº¿
    0.09
    çķĮ线
    0.09
    åĩłæĿ¡
    0.09
    éĢĻæ¢Ŀ
    0.09
    ä¸Ĭä¸ĢæĿ¡
    0.09
    Activations Density 0.015%

    No Known Activations