© 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. 19497
    Prev
    Next
    INDEX
    Explanations

    issue or tissue specific research

    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
    身ä¸ĸ
    -0.08
    åħ¶ä¸º
    -0.08
    itude
    -0.08
     lá»ĵ
    -0.07
    à¹ĥà¸Ī
    -0.07
    gers
    -0.07
    hoff
    -0.07
    ãģ¨ãģĦãģ£ãģ¦
    -0.07
    èģĮå®Ī
    -0.07
     Informazioni
    -0.07
    POSITIVE LOGITS
    ually
    0.11
    /org
    0.10
    à¤Ĺत
    0.08
    éĹ´çļĦ
    0.08
    reate
    0.08
    achs
    0.07
    cule
    0.07
    ืà¹Īà¸Ń
    0.07
    ÑĥÑĢг
    0.07
    elas
    0.07
    Activations Density 0.079%

    No Known Activations