© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    visualizes, likewise, or motor

    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
    ä¸ĭåIJĮ
    -0.10
     appunto
    -0.07
    ãģ®ãģĵãģ¨
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    å°Ķçī¹
    -0.06
    æ¯ĵ
    -0.06
     prom
    -0.06
    é¦ĸåħĪéľĢè¦ģ
    -0.06
    hg
    -0.06
    å°±æĺ¯æľī
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.14
     ebenfalls
    0.14
    ä¹Łæĺ¯ä¸Ģæł·
    0.14
    åIJĮæł·
    0.14
    亦çĦ¶
    0.14
     hingegen
    0.13
    åĪĻæĺ¯
    0.13
     likewise
    0.13
    ä¹ŁåIJĮæł·
    0.13
    åĪĻ
    0.12
    Activations Density 0.023%

    No Known Activations