© 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. 30262
    Prev
    Next
    INDEX
    Explanations

    columns and table layout

    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
     ÑģнизÑĥ
    -0.07
    veld
    -0.07
    é¢łç°¸
    -0.07
    ä¸ĭæĿ¥
    -0.07
    æĽ´å¹´æľŁ
    -0.06
    çĽ¼
    -0.06
    çĿĢçľ¼äºİ
    -0.06
    æª
    -0.06
    ronic
    -0.06
     Gron
    -0.06
    POSITIVE LOGITS
    妻
    0.09
     ÑĪиÑĢи
    0.09
    -width
    0.09
     marginRight
    0.09
    Width
    0.09
     width
    0.08
    çĭŃ
    0.08
    IMI
    0.08
    width
    0.08
     اختصاص
    0.08
    Activations Density 0.018%

    No Known Activations