© 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. 19079
    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
    asca
    -0.08
    æłĹ
    -0.06
    èĥĮ诵
    -0.06
    дали
    -0.06
    etre
    -0.06
    aises
    -0.06
    nant
    -0.06
    asco
    -0.06
    ossen
    -0.06
    æĹłå¤Ħ
    -0.06
    POSITIVE LOGITS
    åħį费注åĨĮ
    0.09
    à¹Ģมà¸Ļ
    0.08
    insi
    0.08
    ä½łå°±ä¼ļ
    0.07
    -Men
    0.07
    atron
    0.07
    åħ´åįİ
    0.07
    åĮ¹
    0.07
    ä¼ļè®©ä½ł
    0.07
     Enti
    0.07
    Activations Density 0.000%

    No Known Activations