© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    directly encrypt or search

    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
    peci
    -0.09
    å°½äºĨ
    -0.09
    åij³çļĦ
    -0.09
    ponsored
    -0.08
    ught
    -0.08
    inous
    -0.08
    unce
    -0.08
    errupted
    -0.08
     ëĺIJíķľ
    -0.08
    avian
    -0.08
    POSITIVE LOGITS
    er
    0.11
    ness
    0.10
    Ø©
    0.10
    اÙĭ
    0.10
    íŀĪ
    0.08
    mente
    0.08
    keit
    0.08
    ly
    0.07
    人
    0.07
    à¸Ļัà¸ļ
    0.07
    Activations Density 0.001%

    No Known Activations