© 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. 9647
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    istributed
    -0.07
    yah
    -0.07
    å¡ijæĸĻåĪ¶åĵģ
    -0.07
    uas
    -0.07
    auga
    -0.07
    uw
    -0.07
    eschi
    -0.07
    _ctxt
    -0.07
     Haft
    -0.07
    æ¦Ĥ
    -0.07
    POSITIVE LOGITS
    æŁIJç§į
    0.09
    æŁIJ个
    0.07
    æŁIJ種
    0.07
    acket
    0.07
    æŁIJåĢĭ
    0.07
    æŁIJ
    0.06
    ale
    0.06
    lege
    0.06
    åľ¨æŁIJ
    0.06
    è¿ĩç¥ŀ
    0.06
    Activations Density 0.016%

    No Known Activations