© 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. 45216
    Prev
    Next
    INDEX
    Explanations

    sitting, waiting, reviewing, addressing

    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
    ÑĢаÑĤно
    -0.09
    ัà¸ĩ
    -0.09
    æĪijä¹Łåİ»
    -0.08
    ochen
    -0.08
    ä¸įæĩĤå¾Ĺ
    -0.08
    ä¸Ĭ课æŶ
    -0.08
     ménage
    -0.08
    åĿ¦çĦ¶
    -0.07
    eltas
    -0.07
    èĢģ人家
    -0.07
    POSITIVE LOGITS
    åĪļä»İ
    0.08
    åĪļ
    0.07
    å·²ç»ıå°Ĩ
    0.07
    æŃ£
    0.06
    çļĦæŃ£
    0.06
    åĪļåĪļ
    0.06
    latin
    0.06
    ÑıÑĤи
    0.06
     nerv
    0.06
     wh
    0.06
    Activations Density 0.305%

    No Known Activations