© 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. 10598
    Prev
    Next
    INDEX
    Explanations

    generating information from 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
    apos
    -0.09
    opoulos
    -0.08
    ìŀ¡
    -0.08
    rott
    -0.08
    utenberg
    -0.07
    íݸ
    -0.07
    utu
    -0.07
    ä¸įåħ¥
    -0.07
    ë²½
    -0.07
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.07
    POSITIVE LOGITS
     extracted
    0.12
    æıIJåıĸ
    0.11
     extraction
    0.10
     Extract
    0.09
     Extraction
    0.09
    Extract
    0.09
     extracting
    0.09
    æıIJçĤ¼
    0.09
     extract
    0.09
    梳çIJĨ
    0.08
    Activations Density 0.004%

    No Known Activations