© 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. 48776
    Prev
    Next
    INDEX
    Explanations

    transcription initiation complex

    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
    å¼ķ以为
    -0.07
    :hidden
    -0.07
    æľĭ
    -0.07
     float
    -0.07
    æĸŃäºĨ
    -0.06
    ä¸Ģæĸ¹çļĦ
    -0.06
    çłģé¾Ħ
    -0.06
    æĸ·
    -0.06
    algo
    -0.06
    åīĶ
    -0.06
    POSITIVE LOGITS
    åķĦ
    0.09
    æŃ£å¼ıåIJ¯åĬ¨
    0.09
    åIJ¯åĬ¨
    0.09
    ä¸ī级
    0.08
    /start
    0.07
     воÑĢ
    0.07
    åįĥ人
    0.07
    semble
    0.07
    å¾ĺ
    0.07
    äºĮåı·
    0.07
    Activations Density 0.016%

    No Known Activations