© 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. 62818
    Prev
    Next
    INDEX
    Explanations

    junction or transition

    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¸Ģå®ļèĥ½
    -0.08
    éģ¥æݧ
    -0.07
    äºĭæĪIJ
    -0.06
    ä¸ĢæĿ¡é¾Ļ
    -0.06
    念念ä¸įå¿ĺ
    -0.06
    rage
    -0.06
    ãĤ³ãĥ¼ãĥ«
    -0.06
    æľīç¦ı
    -0.06
     outcome
    -0.06
    urn
    -0.06
    POSITIVE LOGITS
    è¿ĩ渡
    0.14
     Transition
    0.12
     transition
    0.12
    Transition
    0.11
     transitioning
    0.11
    è¿ŀç»ŃæĢ§
    0.11
     Ãľberg
    0.11
    transition
    0.11
    -transition
    0.11
    _transition
    0.10
    Activations Density 0.150%

    No Known Activations