© 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. 21496
    Prev
    Next
    INDEX
    Explanations

    stronger criterion

    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
    ä¹Łä¸įæĺ¯
    -0.06
    çļĩå¸Ŀ
    -0.06
    ìĹŃ
    -0.06
    ä¹ħ
    -0.06
    åIJŀ
    -0.06
    [-
    -0.06
    ([-
    -0.06
    çİĭ家
    -0.06
    μÏĮ
    -0.06
     assemblies
    -0.06
    POSITIVE LOGITS
    足以
    0.09
    ä¹Łå°±æĦıåij³çĿĢ
    0.08
     implies
    0.08
     posix
    0.08
    impl
    0.08
     implying
    0.08
     unthinkable
    0.08
    æĹ¢æĺ¯
    0.08
    æĹ¢èĥ½
    0.07
    ä»İæł¹æľ¬ä¸Ĭ
    0.07
    Activations Density 0.055%

    No Known Activations