© 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. 60184
    Prev
    Next
    INDEX
    Explanations

    out-parameter, similarly, folded twice, open, typing

    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
     **
    -0.06
    2
    -0.06
    èij
    -0.05
    åĪ»
    -0.05
     bona
    -0.05
    ä¾ĭ
    -0.05
    客
    -0.05
    Optimizer
    -0.05
    l
    -0.05
    æħ§
    -0.05
    POSITIVE LOGITS
    类似çļĦ
    0.10
    ä¹Łæĺ¯å¦ĤæѤ
    0.10
     similarly
    0.10
    ä¹Łæĺ¯ä¸Ģæł·
    0.10
    ä¾ĿçĦ¶åľ¨
    0.10
    åIJĮæł·
    0.09
     ebenfalls
    0.09
    åIJĮ樣
    0.09
    类似éĹ®é¢ĺ
    0.09
    اء
    0.09
    Activations Density 0.063%

    No Known Activations