© 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. 38346
    Prev
    Next
    INDEX
    Explanations

    treatment apparatus | height . | 1 inhibition | Revolution " | p *

    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
    ↵
    -0.06
    T
    -0.06
    -0.06
    ãĢĢ
    -0.06
    æĺ¯æĮĩåľ¨
    -0.05
     [
    -0.05
     J
    -0.05
    CS
    -0.05
    -0.05
     mentioned
    -0.05
    POSITIVE LOGITS
    ä¹Łè¢«ç§°ä¸º
    0.10
     famously
    0.09
    稱çĤº
    0.09
    åıĪ称为
    0.09
    æľĢèijĹåIJįçļĦ
    0.09
    称为
    0.09
    nemonic
    0.09
    åıĪåı«
    0.09
    erken
    0.09
    .allowed
    0.09
    Activations Density 0.019%

    No Known Activations