© 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. 24053
    Prev
    Next
    INDEX
    Explanations

    's followed by 'un', 'one', 'a', 'second'

    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
    ught
    -0.08
    æĹłæģĻ
    -0.08
    ä¸įåIJĮç¨ĭ度
    -0.08
    ertest
    -0.07
    angelog
    -0.07
    TypeInfo
    -0.07
    æīĢ欲
    -0.07
    oty
    -0.07
    igsaw
    -0.07
    niku
    -0.07
    POSITIVE LOGITS
     insomma
    0.08
    ô
    0.07
     an
    0.07
     vorba
    0.06
    ta
    0.06
     testament
    0.06
     a
    0.06
     wiÄĻc
    0.06
    .Executor
    0.06
    zh
    0.06
    Activations Density 0.333%

    No Known Activations