© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    Tempeñ–Lie, Clark, queen, Ru

    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
    ation
    -0.15
    ÏĤ
    -0.11
    Ø©
    -0.11
    ness
    -0.11
    emente
    -0.10
    ãģ¾ãģ¾
    -0.10
    à§įত
    -0.10
    ization
    -0.09
    ениÑı
    -0.09
    ÙĬÙģ
    -0.09
    POSITIVE LOGITS
    ãĥ³
    0.10
    zelfde
    0.10
    bidden
    0.09
    ers
    0.09
    gether
    0.09
    raries
    0.08
    Ùĩ
    0.08
    åIJĦç§įåIJĦæł·
    0.08
    顾åIJįæĢĿ
    0.08
    zeitig
    0.08
    Activations Density 0.042%

    No Known Activations