© 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. 20933
    Prev
    Next
    INDEX
    Explanations

    pagination or court cases

    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
    vell
    -0.07
     Ger
    -0.06
    forme
    -0.06
    ytt
    -0.06
    åij¨åĪĬ
    -0.06
    åĺī
    -0.06
    çħ§é¡¾å¥½
    -0.06
     tie
    -0.06
     sailed
    -0.06
     motor
    -0.06
    POSITIVE LOGITS
    ç¼ĸè¾ijäºİ
    0.09
    ANTES
    0.08
    pag
    0.08
    ä¸Ĭä¸Ģ页
    0.08
    ÏĢÏĮ
    0.08
    æľīè¯Ŀ
    0.08
    ×ķ×ij×Ķ
    0.08
    ÙĦاÙĨ
    0.07
    olla
    0.07
    Pagination
    0.07
    Activations Density 0.060%

    No Known Activations