© 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. 33481
    Prev
    Next
    INDEX
    Explanations

    material objects and substances

    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
    ä¹ĺçĿĢ
    -0.06
    çģµçŁ³
    -0.06
     bust
    -0.06
     governing
    -0.06
     achieved
    -0.06
     published
    -0.06
    å±ĤéĿ¢ä¸Ĭ
    -0.06
     Cons
    -0.06
    该æľīçļĦ
    -0.06
    æĸ°åĬłåĿ¡
    -0.05
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    好åij¢
    0.08
    éĢģä¸Ģ
    0.08
    æł¹æľ¬ä¸Ĭ
    0.08
    ignet
    0.08
    ụt
    0.08
     ÑıкобÑĭ
    0.08
    ieber
    0.07
    пÑĢом
    0.07
     statt
    0.07
    Activations Density 0.019%

    No Known Activations