© 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. 45073
    Prev
    Next
    INDEX
    Explanations

    transitional states, pre-diabetes, transparent

    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
    æĹłæļĩ
    -0.08
    ç®Ģæ´ģ
    -0.08
    ft
    -0.07
     plain
    -0.07
    ç´ł
    -0.07
    ä¸įå¤ĸ
    -0.07
    ä¸įè¨Ģ
    -0.07
    usi
    -0.07
    æĹłè¨Ģ
    -0.07
    æĹłçĥŁ
    -0.07
    POSITIVE LOGITS
    è¿ĩ渡
    0.13
    ä»ĭäºİ
    0.13
     transitional
    0.13
    _partial
    0.11
     grad
    0.11
     Transitional
    0.10
     transitioning
    0.10
    æ¸IJåıĺ
    0.10
     gradually
    0.10
     Ãľberg
    0.09
    Activations Density 0.216%

    No Known Activations