© 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. 40552
    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
    inerary
    -0.10
    åĦ¿çļĦ
    -0.10
    jenigen
    -0.10
    ffects
    -0.09
    anship
    -0.09
    çİ°åľ¨çļĦä½įç½®
    -0.09
    ndice
    -0.09
    ponsor
    -0.09
    IData
    -0.08
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    -0.08
    POSITIVE LOGITS
    主ä¹īèĢħ
    0.06
     (
    0.06
    âĢij
    0.06
    å°±
    0.06
    æľīäºĶ
    0.06
    /
    0.06
    -
    0.05
    çļĦ温æļĸ
    0.05
     ça
    0.05
    çŁ¥åIJįåĵģçīĮ
    0.05
    Activations Density 0.593%

    No Known Activations

    This feature has no known activations.