© 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. 64124
    Prev
    Next
    INDEX
    Explanations

    many of these

    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»»ä½ķå½¢å¼ıçļĦ
    -0.09
    ä¹Łä¸įå¤ļ
    -0.09
     whichever
    -0.09
     whatever
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.08
    whatever
    -0.08
    太å°ij
    -0.08
    ாத
    -0.08
    æĽ´ä¸įä¼ļ
    -0.08
    祺
    -0.08
    POSITIVE LOGITS
     antaranya
    0.07
    uns
    0.07
    åı¯çĽ´æİ¥
    0.06
     shar
    0.06
    ugo
    0.06
    æĺ¯çĽ´æİ¥
    0.06
    cular
    0.06
     overlap
    0.06
     overlaps
    0.06
    ones
    0.06
    Activations Density 0.397%

    No Known Activations