© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30193
    Prev
    Next
    INDEX
    Explanations

    information, license, links, description

    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
     Acres
    -0.08
    太æŀģ
    -0.07
    umbing
    -0.07
    ériment
    -0.07
    çŁ¥éģĵæĪij
    -0.07
    ä¸įéĶĻ
    -0.07
    _EXTERNAL
    -0.07
    utenberg
    -0.06
    åħĥéĴ±
    -0.06
    ä¸ĩç¾İåħĥ
    -0.06
    POSITIVE LOGITS
    详è§ģ
    0.12
    详æĥħ请
    0.11
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.09
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.09
    代çłģå¦Ĥä¸ĭ
    0.09
    è§ģéĻĦ件
    0.09
     detailed
    0.09
     подÑĢобно
    0.08
    请åıĤéĺħ
    0.08
     HERE
    0.08
    Activations Density 0.717%

    No Known Activations