© 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. 46597
    Prev
    Next
    INDEX
    Explanations

    intermediate

    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
    /document
    -0.08
    åı¦ä¸Ģ端
    -0.08
    éĢĨè¡Į
    -0.08
    -document
    -0.07
    æľ¬æł¼
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.07
    å±±åİ¿
    -0.07
    _ENCODE
    -0.07
    ongen
    -0.07
    ẩy
    -0.07
    POSITIVE LOGITS
    ä»ĭäºİ
    0.25
     intermediate
    0.23
     Intermediate
    0.20
    æĹ¢ä¸į
    0.18
    Intermediate
    0.18
    æĹ¢
    0.18
    ä¸ŃéĹ´
    0.18
     neither
    0.17
     intermedi
    0.17
     hybrid
    0.16
    Activations Density 0.248%

    No Known Activations