© 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. 19736
    Prev
    Next
    INDEX
    Explanations

    seamless connections and transitions

    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
     Gabin
    -0.08
    æĽ´å¤ļ精彩åĨħ容
    -0.08
     íĥģ
    -0.08
    _SCOPE
    -0.08
    дев
    -0.07
    åįĵ
    -0.07
    _DIST
    -0.07
    å®ŀçݰ对
    -0.07
    antry
    -0.07
    .poll
    -0.07
    POSITIVE LOGITS
    è¡Ķæİ¥
    0.17
    æĹłç¼Ŀ
    0.16
    è¿ĩ渡
    0.15
     seamless
    0.13
     transition
    0.13
     seamlessly
    0.13
    transition
    0.12
     continuity
    0.12
     Transition
    0.12
    Transition
    0.11
    Activations Density 0.008%

    No Known Activations