© 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. 20248
    Prev
    Next
    INDEX
    Explanations

    related to information details

    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
    åıªè¦ģ
    -0.08
    åİŁåĽłå°±æĺ¯
    -0.07
     proper
    -0.07
    åıªè¦ģåľ¨
    -0.06
    ÐķС
    -0.06
    proper
    -0.06
    пле
    -0.06
    誰ãģ§ãĤĤ
    -0.06
     sekaligus
    -0.06
     sino
    -0.06
    POSITIVE LOGITS
     ÙĪÙĩÙĦ
    0.12
     vs
    0.12
    æĺ¯åIJ¦æľī
    0.12
    æĺ¯åIJ¦åŃĺåľ¨
    0.11
    æľī没æľī
    0.11
     ÙĪÙĥÙĬÙģ
    0.11
    æĺ¯åIJ¦ä¼ļ
    0.11
    æĺ¯åIJ¦éľĢè¦ģ
    0.11
    æľīåĵªäºĽ
    0.11
    ä¼ļä¸įä¼ļ
    0.11
    Activations Density 0.062%

    No Known Activations