© 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. 12737
    Prev
    Next
    INDEX
    Explanations

    java imports of .io and .util

    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
    heimer
    -0.09
    heim
    -0.08
    pher
    -0.08
    çļĭ
    -0.08
    agnost
    -0.07
    峪
    -0.07
    ist
    -0.07
    åĽĽè½®
    -0.07
    åı¯æĢķ
    -0.06
    /modules
    -0.06
    POSITIVE LOGITS
    gota
    0.08
     Boa
    0.07
    بÙĬر
    0.07
    ":"/
    0.07
    ","#
    0.06
    èģĺ
    0.06
     ë¹ł
    0.06
    neu
    0.06
    á»Ńa
    0.06
    mira
    0.06
    Activations Density 0.173%

    No Known Activations