© 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. 64898
    Prev
    Next
    INDEX
    Explanations

    dimension or count

    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
    亿ä¸ĩ
    -0.08
    æĪĸåħ¶
    -0.08
     millions
    -0.07
     Millions
    -0.07
    à¥įव
    -0.07
    åĩłåįģä¸ĩ
    -0.07
    ãģĭãģ¯
    -0.07
    份é¢Ŀ
    -0.07
    umm
    -0.07
     thousands
    -0.07
    POSITIVE LOGITS
    =len
    0.08
    idel
    0.07
    ä¸Ģè¡Į
    0.07
    .ndim
    0.07
    ÑĩеÑĤов
    0.07
    è¡Įæķ°
    0.07
    æĹłåĩł
    0.07
    roits
    0.06
    æĸĻçIJĨ
    0.06
    len
    0.06
    Activations Density 0.004%

    No Known Activations