© 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. 21680
    Prev
    Next
    INDEX
    Explanations

    enable extension or recovery

    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
    пÑĢоÑĩем
    -0.07
    agl
    -0.07
    è¶Ĭå°ij
    -0.07
    è¶Ĭå¿«
    -0.07
    æıIJéĺ²
    -0.07
    ä¸ĢçĶŁ
    -0.07
    å¼ı
    -0.07
    ebin
    -0.07
     aang
    -0.07
    aget
    -0.07
    POSITIVE LOGITS
     otherwise
    0.13
     altrimenti
    0.12
    åİŁæľ¬
    0.11
    åIJ¦åĪĻ
    0.10
    çªģçł´äºĨ
    0.09
    åİŁæľ¬æĺ¯
    0.09
    otherwise
    0.09
    åİŁæĿ¥
    0.09
    åİŁæĿ¥æĺ¯
    0.09
     without
    0.09
    Activations Density 0.327%

    No Known Activations