© 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. 19424
    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
    evity
    -0.09
    ä¸Ģæ°Ķ
    -0.08
     met
    -0.07
     Undang
    -0.07
    <|box_end|>
    -0.07
    çļĦè§ĦåĪĻ
    -0.07
     gereken
    -0.07
    åı£ä¸ŃçļĦ
    -0.06
    è¾īæĺł
    -0.06
     theoretically
    -0.06
    POSITIVE LOGITS
    æĪªæŃ¢çĽ®åīį
    0.07
    ëį°
    0.07
    greg
    0.07
    åIJĥä¸ĢäºĽ
    0.07
    ATAN
    0.07
    lico
    0.07
    ç»ıæµİæĬĢæľ¯
    0.07
    zec
    0.07
    atetime
    0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.07
    Activations Density 0.000%

    No Known Activations