© 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. 57174
    Prev
    Next
    INDEX
    Explanations

    exclusively focus on data

    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
    heimer
    -0.08
    ennen
    -0.07
    à¤ļà¥įà¤Ľ
    -0.07
    isor
    -0.07
     sno
    -0.07
    å¼¥
    -0.07
    æ¯ĶåĪ«äºº
    -0.07
    kh
    -0.07
    ä¸įçĶĺ
    -0.06
     adapt
    -0.06
    POSITIVE LOGITS
    ä¸įåĮħæĭ¬
    0.14
    ä¸ĵ注äºİ
    0.13
     exclusively
    0.13
     ONLY
    0.12
    åıª
    0.12
     focus
    0.12
    ä¸įåĮħåIJ«
    0.12
    éĽĨä¸Ńç²¾åĬĽ
    0.11
    ä»ĸåıª
    0.11
     excludes
    0.11
    Activations Density 0.105%

    No Known Activations