© 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. 22259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸Ĭ天
    -0.07
     Bourg
    -0.07
    adora
    -0.07
    borg
    -0.07
    pace
    -0.07
    uwe
    -0.07
    ador
    -0.06
    leur
    -0.06
    qw
    -0.06
    (formatter
    -0.06
    POSITIVE LOGITS
    âĪĴ
    0.07
     Garan
    0.07
    ndon
    0.07
    ï¼ģï¼Ł
    0.07
     nale
    0.07
    åħĭèIJ¨æĸ¯
    0.07
    å·¥ä½ľæĢĿè·¯
    0.07
    ï¼ļ</
    0.06
    èĵ¬èݱ
    0.06
    å§Ĩæĸ¯
    0.06
    Activations Density 0.000%

    No Known Activations