© 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. 65037
    Prev
    Next
    INDEX
    Explanations

    units of length or counting

    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
    人ä¸Ģ
    -0.09
    æ¹ĥ
    -0.09
    zung
    -0.08
    年审
    -0.08
    emoc
    -0.08
    emy
    -0.07
    бен
    -0.07
    irit
    -0.07
    ä¸īè·¯
    -0.07
    ItemClick
    -0.07
    POSITIVE LOGITS
    æķ°çļĦ
    0.10
    æķ°ä¸º
    0.09
    æķ°
    0.09
    -long
    0.09
    æķ°åĴĮ
    0.08
    ar
    0.08
    éĹ´çļĦ
    0.08
    éĹ´
    0.08
     подÑĢÑıд
    0.08
    æķ°æĺ¯
    0.08
    Activations Density 0.161%

    No Known Activations