© 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. 62613
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    ambo
    -0.08
     ÑĤоже
    -0.08
     likewise
    -0.08
     nowhere
    -0.07
    åĨįä¸į
    -0.07
    ä¸įæĺ¯å¾Ī
    -0.07
    без
    -0.07
     otherwise
    -0.07
    èĻ½çĦ¶æĺ¯
    -0.07
    åIJ¦åĪĻä¼ļ
    -0.07
    POSITIVE LOGITS
    Ø©
    0.09
     instead
    0.09
    Instead
    0.08
    ores
    0.08
     Instead
    0.08
    ment
    0.08
     focus
    0.08
    ness
    0.07
    åıĸèĢĮ代ä¹ĭ
    0.07
    instead
    0.07
    Activations Density 0.037%

    No Known Activations