© 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. 3783
    Prev
    Next
    INDEX
    Explanations

    notation and abbreviations

    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
    hout
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    rollo
    -0.08
    æijĨåľ¨
    -0.07
    lables
    -0.07
    æĸ¯åħĭ
    -0.07
    -Headers
    -0.07
     :+:
    -0.07
    ãģĸãģ¾
    -0.07
    åIJĪæł¼çļĦ
    -0.07
    POSITIVE LOGITS
    ayu
    0.07
    vir
    0.07
    åĴĮéĹ®é¢ĺ
    0.07
    äºĶæĮĩ
    0.06
    åħ«éĥ¨
    0.06
    blah
    0.06
    abis
    0.06
    ä¸Ģ大
    0.06
    åĵĢ
    0.06
    veh
    0.06
    Activations Density 0.001%

    No Known Activations