© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42435
    Prev
    Next
    INDEX
    Explanations

    represents

    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
    usp
    -0.07
    lund
    -0.07
    byname
    -0.07
    æľīåĬł
    -0.07
    ufen
    -0.07
    ad
    -0.07
    usin
    -0.07
    ä¸ĵäººè´Łè´£
    -0.06
    jsonp
    -0.06
    åģļå¾Ĺ
    -0.06
    POSITIVE LOGITS
    সà§įয
    0.07
     :\
    0.07
    æĢªçļĦ
    0.07
    å¹´åįİ
    0.07
    onos
    0.07
    resents
    0.07
    icks
    0.07
    åİĨ
    0.06
    éªĦéĺ³
    0.06
    æĢª
    0.06
    Activations Density 0.008%

    No Known Activations