© 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. 40008
    Prev
    Next
    INDEX
    Explanations

    advertisement or ADVERTISEMENT

    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
    å¿«å¿«ä¹IJ
    -0.08
    hver
    -0.08
    ombok
    -0.07
    kker
    -0.07
    ä¸įè¿ĺ
    -0.07
    Xuất
    -0.07
    coce
    -0.07
    .googlecode
    -0.07
    Strings
    -0.07
    ADER
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    :
    0.07
    illa
    0.07
     article
    0.07
     rese
    0.06
    ä¸Ĭä¸Ģç¯ĩ
    0.06
    ï¼ļ
    0.06
    arno
    0.06
     artic
    0.06
    ä¸Ĭä¸Ģ
    0.06
    Activations Density 0.216%

    No Known Activations