© 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. 58605
    Prev
    Next
    INDEX
    Explanations

    examples and explanations

    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
    åIJįåī¯
    -0.09
    regor
    -0.08
     legislat
    -0.08
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    æĤĶ
    -0.07
    鱿
    -0.07
     liá»ĩt
    -0.07
    auen
    -0.07
    ewe
    -0.07
    _modes
    -0.07
    POSITIVE LOGITS
     analog
    0.08
     analogy
    0.07
    ç±»æ¯Ķ
    0.07
     esplic
    0.07
    æ¯Ķåĸ»
    0.07
    fique
    0.06
    à¸Ńà¸¸à¸Ľ
    0.06
    çIJĨ解
    0.06
     explain
    0.06
    çļĦæľĭåıĭåı¯ä»¥
    0.06
    Activations Density 0.012%

    No Known Activations