© 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. 55477
    Prev
    Next
    INDEX
    Explanations

    code file paths and imports

    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
    ä»Ĺ
    -0.08
    主æĦı
    -0.08
    rie
    -0.07
    æĥŁæľī
    -0.07
    åħĭ鼷
    -0.07
    nez
    -0.07
    ourg
    -0.07
    usting
    -0.07
    zun
    -0.06
    زÙĪ
    -0.06
    POSITIVE LOGITS
    fäl
    0.07
    yli
    0.07
    Headers
    0.07
    awi
    0.07
    asseur
    0.06
    wake
    0.06
    esian
    0.06
    aron
    0.06
    è´¢
    0.06
    çĪ±æ°ij
    0.06
    Activations Density 0.001%

    No Known Activations