© 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. 61998
    Prev
    Next
    INDEX
    Explanations

    variations of various and respective

    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
    erma
    -0.08
    izen
    -0.08
    活水
    -0.07
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.07
    ثاÙĦ
    -0.07
    Ùĭ
    -0.07
    ezu
    -0.07
    ä¸ĩåį·
    -0.07
     Dasar
    -0.07
    æķ´ä¸ªä¸ĸçķĮ
    -0.07
    POSITIVE LOGITS
    ãĢħãģ®
    0.11
    ãĢħãģĮ
    0.09
    ÑĬв
    0.09
     macam
    0.08
    å¼ĤçļĦ
    0.08
     Äijặn
    0.08
    æīĢåij¨
    0.08
    EMENT
    0.08
    ç´§è¦ģ
    0.08
    днев
    0.08
    Activations Density 0.007%

    No Known Activations