© 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. 24604
    Prev
    Next
    INDEX
    Explanations

    challenging established ideas or faith

    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
     recip
    -0.07
    æĢ§åŃIJ
    -0.07
    è°ģä¹Ł
    -0.07
    èĢĮéĿŀ
    -0.07
    icy
    -0.06
    å¹³
    -0.06
    cy
    -0.06
    lice
    -0.06
    _Native
    -0.06
    uably
    -0.06
    POSITIVE LOGITS
     overly
    0.09
    ç¹ģçIJIJ
    0.09
    èĻļ伪
    0.09
    æľīä»»ä½ķ
    0.09
    åľ¨ä»ĸçľĭæĿ¥
    0.09
    ä»»ä½ķå½¢å¼ıçļĦ
    0.08
     unnecessarily
    0.08
     blindly
    0.08
     claims
    0.08
     ÑģлиÑĪком
    0.08
    Activations Density 0.139%

    No Known Activations