© 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. 2759
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical terms

    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
    oup
    -0.08
    çĦ¶åIJİæĬĬ
    -0.07
     lump
    -0.07
    fet
    -0.07
    æĿ¿ä¸Ĭ
    -0.07
    órd
    -0.07
     separation
    -0.07
    herr
    -0.07
    _hdl
    -0.07
    -production
    -0.06
    POSITIVE LOGITS
    idik
    0.08
    aimer
    0.07
    iane
    0.07
    .normalized
    0.07
     directions
    0.07
    æĭ¿åİ»
    0.07
    orros
    0.07
    ä¿Ĭ
    0.07
    à¥Ī
    0.07
    acara
    0.07
    Activations Density 0.003%

    No Known Activations