© 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. 4243
    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
    lop
    -0.07
    å¿į
    -0.07
    éľ²
    -0.06
    寸
    -0.06
    rash
    -0.06
    丽
    -0.06
    à¹Ħà¸Ĥ
    -0.06
    æĢ
    -0.06
    èĢĮçŁ¥
    -0.06
    /file
    -0.06
    POSITIVE LOGITS
    ä¿¡æģ¯çĶ±
    0.07
    taki
    0.07
    usin
    0.07
    è®
    0.07
    ional
    0.06
     seperate
    0.06
    даÑħ
    0.06
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.06
    hier
    0.06
    añ
    0.06
    Activations Density 0.000%

    No Known Activations