© 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. 31371
    Prev
    Next
    INDEX
    Explanations

    uppercase and lowercase letters

    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
    chern
    -0.09
    ArrayOf
    -0.08
    åĮ»å¾·
    -0.08
    autore
    -0.08
    ứ
    -0.07
    Builders
    -0.07
    wagon
    -0.07
     Bento
    -0.07
    çł´äº§
    -0.07
    cott
    -0.07
    POSITIVE LOGITS
    ought
    0.07
     letters
    0.07
     letter
    0.07
    _upper
    0.07
    磫æŃ£
    0.06
    åļ¼
    0.06
    åŃĹæ¯į
    0.06
    olle
    0.06
     letterSpacing
    0.06
    Letters
    0.06
    Activations Density 0.013%

    No Known Activations