© 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. 43702
    Prev
    Next
    INDEX
    Explanations

    Korean names and places

    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
    Ø©
    -0.11
    纷åijĪ
    -0.09
    Ùĭ
    -0.09
    fication
    -0.09
    occhi
    -0.09
    udio
    -0.08
    hood
    -0.08
    ories
    -0.08
    ÒĻ
    -0.08
    Ù°
    -0.08
    POSITIVE LOGITS
    nya
    0.13
    sett
    0.10
    set
    0.09
     lá»ĵ
    0.09
    ned
    0.09
    ser
    0.09
    spor
    0.09
    ship
    0.09
    à¸Ħà¹Į
    0.09
    raft
    0.08
    Activations Density 0.116%

    No Known Activations