© 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. 1680
    Prev
    Next
    INDEX
    Explanations

    rounding with decimal places

    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
    æ¯Ķå¦Ĥ
    -0.08
    ัà¸Ļà¸ĺà¹Į
    -0.07
     Gors
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    å½»
    -0.07
    iec
    -0.07
    outu
    -0.07
    arate
    -0.07
    羣åģĩ
    -0.07
    让å®ĥ们
    -0.07
    POSITIVE LOGITS
    å¦į
    0.08
    (--
    0.07
    loch
    0.07
     arro
    0.07
    ä¸ĭåIJĮ
    0.06
    bum
    0.06
    unch
    0.06
    å¸ĮæľĽå¯¹å¤§å®¶
    0.06
    EDE
    0.06
    çĵ¶ä¸Ń
    0.06
    Activations Density 0.004%

    No Known Activations