© 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. 19706
    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
    atta
    -0.07
    åIJĴ
    -0.07
    ÑĢай
    -0.07
    ä½ĵèĤ²ä¸Ńå¿ĥ
    -0.07
    æĶ¿åįıåī¯ä¸»å¸Ń
    -0.07
    mi
    -0.07
    akis
    -0.06
    åİ¿çļĦ
    -0.06
     aÈĻa
    -0.06
    æŃ»æ´»
    -0.06
    POSITIVE LOGITS
    åīįèĢħ
    0.07
    amat
    0.07
    微信æī«ä¸Ģæī«
    0.07
    èĢIJå¿ĥçļĦ
    0.07
    _BEFORE
    0.07
    UserProfile
    0.07
    <AM
    0.07
    ifu
    0.07
    缸è§ģ
    0.07
    ëĮĢë¹Ħ
    0.07
    Activations Density 0.000%

    No Known Activations