© 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. 50923
    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
    issing
    -0.08
    áĥĺáĥª
    -0.08
    å°ijéĥ¨åĪĨ
    -0.08
    idas
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    elan
    -0.08
    eker
    -0.07
    è¯Ħ为
    -0.07
    æĸ¯åħĭ
    -0.07
    POSITIVE LOGITS
    assis
    0.07
    رØŃ
    0.07
    bach
    0.07
    arty
    0.06
    ä¹ĭåIJİåĨį
    0.06
    rocess
    0.06
    aster
    0.06
    asts
    0.06
    hofer
    0.06
     cul
    0.06
    Activations Density 0.000%

    No Known Activations