© 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. 24943
    Prev
    Next
    INDEX
    Explanations

    comparative structure (X-er the Y)

    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
    追
    -0.08
    æİĪ
    -0.07
    Web
    -0.07
     ard
    -0.07
    åħ¶ä»ĸ
    -0.07
    _
    -0.06
    使çĶ¨
    -0.06
    åĴĮåħ¶ä»ĸ
    -0.06
     Web
    -0.06
    åħ¨
    -0.06
    POSITIVE LOGITS
    è¶Ĭ好
    0.19
    è¶Ĭ强
    0.16
    è¶Ĭ大
    0.15
    è¶Ĭé«ĺ
    0.15
    ìĪĺë¡Ŀ
    0.14
    è¶Ĭå¿«
    0.14
    è¶Ĭæĺ¯
    0.14
    è¶Ĭå¤ļ
    0.13
    è¶Ĭéķ¿
    0.13
    è¶Ĭå°ij
    0.13
    Activations Density 0.037%

    No Known Activations