© 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. 22320
    Prev
    Next
    INDEX
    Explanations

    trailing slashes or numbers at the end

    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
    azu
    -0.08
     nasce
    -0.08
    örde
    -0.07
    å¥Īä½ķ
    -0.07
    å°Ķå¾·
    -0.07
     mornings
    -0.07
    lle
    -0.07
    æĹ©æĻ¨
    -0.07
    middel
    -0.07
    _starts
    -0.07
    POSITIVE LOGITS
    =end
    0.10
    åĴĮåīį
    0.09
    å°¾
    0.09
    æľ«ç«¯
    0.08
     end
    0.08
    ä¸įå¿ĺ
    0.08
    æĶ¶å°¾
    0.08
    ç»ĵå°¾
    0.07
    ä¸İåīį
    0.07
    (end
    0.07
    Activations Density 0.058%

    No Known Activations