© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    amateur and independent pursuits

    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
    icity
    -0.08
    iterals
    -0.07
    èĪĮ
    -0.07
    ropp
    -0.07
    IENT
    -0.07
     Cardoso
    -0.07
    inou
    -0.07
     Bernstein
    -0.07
    ä¸į说è¯Ŀ
    -0.07
    COOKIE
    -0.07
    POSITIVE LOGITS
    /small
    0.10
    æĪĸå°ı
    0.09
    ä¹ĭçİĭ
    0.09
    /local
    0.09
    /private
    0.08
    /dom
    0.07
    å±ħå¤ļ
    0.07
    /home
    0.07
    lore
    0.07
     versus
    0.07
    Activations Density 0.402%

    No Known Activations