© 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. 7440
    Prev
    Next
    INDEX
    Explanations

    boundaries, regions, and domains

    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
    èĭ¥æľī
    -0.08
    íķŃ
    -0.07
    å²Ń
    -0.07
     Bison
    -0.07
    ä¸Ģ身
    -0.07
    cano
    -0.07
    åįķ项
    -0.07
    mlink
    -0.07
     spaced
    -0.07
    æĽ¿
    -0.07
    POSITIVE LOGITS
     bounded
    0.11
     boundaries
    0.11
    è¾¹çķĮ
    0.10
     bordered
    0.10
     enclosed
    0.09
    å½¢çĬ¶çļĦ
    0.09
    å½¢çĬ¶
    0.09
     delimited
    0.09
     rectangular
    0.09
     airspace
    0.09
    Activations Density 0.027%

    No Known Activations