© 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. 41539
    Prev
    Next
    INDEX
    Explanations

    therefore, thus, so

    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
    qip
    -0.08
    oard
    -0.08
    -generic
    -0.07
    plorer
    -0.07
    åĿĽ
    -0.07
     Prim
    -0.07
    çĴ¨
    -0.07
     ведÑĮ
    -0.07
    äºİä¸Ģ
    -0.07
     przecież
    -0.07
    POSITIVE LOGITS
    åħ»æĪIJèī¯å¥½çļĦ
    0.07
    è¿ĩ好
    0.07
    æİĮæı¡å¥½
    0.07
    æľīå¿ħè¦ģ
    0.07
    è°¨éĺ²
    0.06
    ä¸įæĺ¯å¾Ī好
    0.06
    è´§åĪ°ä»ĺ款
    0.06
    Ø´Ùģ
    0.06
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.06
    谨记
    0.06
    Activations Density 0.006%

    No Known Activations