© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16968
    Prev
    Next
    INDEX
    Explanations

    compute the output

    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
    ness
    -0.11
    Ø©
    -0.09
    hood
    -0.09
    å¾Ĺä½ı
    -0.08
    age
    -0.07
    uva
    -0.07
    ged
    -0.07
    quist
    -0.07
    issement
    -0.07
    born
    -0.07
    POSITIVE LOGITS
    åĻ¨çļĦ
    0.10
    igny
    0.09
    /cal
    0.09
    enance
    0.09
    InChildren
    0.09
     ulang
    0.09
    /render
    0.09
    ulative
    0.08
    åĩºæĿ¥çļĦ
    0.08
    رسÛĮ
    0.08
    Activations Density 0.037%

    No Known Activations