© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9181
    Prev
    Next
    INDEX
    Explanations

    smallest sigma-algebra

    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
    epend
    -0.06
    gid
    -0.06
    æīĢåѦçļĦ
    -0.06
    åĩ¯è¿ª
    -0.06
    intel
    -0.06
    çŃī设å¤ĩ
    -0.06
    bm
    -0.06
    åĬŀåħ¬è®¾å¤ĩ
    -0.06
    æľ¬äººåľ¨
    -0.06
    éķ¿åĬ¿
    -0.06
    POSITIVE LOGITS
    elter
    0.08
    bacher
    0.08
     addTarget
    0.08
    Fizz
    0.07
    ustering
    0.07
    hamn
    0.07
    ValueCollection
    0.07
    á»°
    0.07
    ushing
    0.07
    uffman
    0.07
    Activations Density 0.011%

    No Known Activations