© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    multi/bi-functional/valent/variate

    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
     ÙĥÙĦÙĩ
    -0.08
    åĴĮå¤ĦçIJĨ
    -0.08
    ber
    -0.08
    lessly
    -0.08
     मातà¥įर
    -0.08
    åĬĽè¡Į
    -0.08
    tify
    -0.08
    kop
    -0.07
    izen
    -0.07
    家åĸ»
    -0.07
    POSITIVE LOGITS
    åĴĮå¤ļ
    0.13
    imensional
    0.12
    æĪĸå¤ļ
    0.12
    /single
    0.10
    -mult
    0.09
    iplinary
    0.09
    /m
    0.08
     (>
    0.08
    /oct
    0.08
    å°¤åħ¶æĺ¯
    0.08
    Activations Density 0.118%

    No Known Activations