© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    尼迪
    -0.07
    едÑĭ
    -0.07
    ë©ĺ
    -0.07
     CNBC
    -0.06
    èµĮ
    -0.06
    (;
    -0.06
    ä¹ĭæĺŁ
    -0.06
    à¥įला
    -0.06
    actory
    -0.06
    è§ģè¯ģ
    -0.06
    POSITIVE LOGITS
    ToShow
    0.09
    Showing
    0.08
    ض
    0.07
    ndata
    0.07
    va
    0.07
    åIJİåı°
    0.07
     Showing
    0.07
    Ma
    0.07
     Ma
    0.07
    _Show
    0.07
    Activations Density 0.460%

    No Known Activations