© 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. 55631
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    ÙĦÙĬÙĦ
    -0.07
    quare
    -0.07
    ãĤ¸ãĥ³
    -0.07
    hiri
    -0.07
    åĵī
    -0.07
    èĩªéĢī
    -0.07
    daq
    -0.07
    ä¸įèµ·æĿ¥
    -0.07
    涮
    -0.06
     мÑĥд
    -0.06
    POSITIVE LOGITS
    urras
    0.07
    ifes
    0.07
    EME
    0.07
    olling
    0.07
    çķĻ
    0.07
     Gle
    0.07
    iclo
    0.07
    è·Łäºº
    0.07
    çķĻæľī
    0.07
     annonces
    0.07
    Activations Density 0.002%

    No Known Activations