© 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. 50836
    Prev
    Next
    INDEX
    Explanations

    lower numbers, 2, instead

    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
    λÏİν
    -0.08
    延åºĨ
    -0.07
    ilia
    -0.07
    ellos
    -0.07
    éĽıå½¢
    -0.06
    å¾ĹåIJį
    -0.06
    ASIC
    -0.06
    ä¸įå¤ļ说
    -0.06
    remark
    -0.06
    à°Ĺà±ģ
    -0.06
    POSITIVE LOGITS
     instead
    0.11
     вмеÑģÑĤо
    0.09
    æĶ¹ä¸º
    0.09
    instead
    0.09
    à¸ģวà¹Īาà¹Ģà¸Ķิม
    0.09
    æĶ¹çĶ¨
    0.08
    åIJĮæł·çļĦ
    0.08
    åľ¨åİŁ
    0.08
     Instead
    0.08
    Instead
    0.08
    Activations Density 0.042%

    No Known Activations