© 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. 33749
    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
    ubr
    -0.07
    opan
    -0.07
    æŶåĢĻ
    -0.07
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.07
    ato
    -0.06
    uro
    -0.06
    áĢ±áĢ¸
    -0.06
    æĿ¥çļĦæŶåĢĻ
    -0.06
    ä¹Łåıªæľī
    -0.06
     Marriott
    -0.06
    POSITIVE LOGITS
    ype
    0.10
    åIJĦèĩªçļĦ
    0.07
    ypes
    0.07
    éŁ³å£°
    0.07
    ä¼¼æĺ¯
    0.07
    ackers
    0.07
    ÑģкÑĢÑĭ
    0.07
    ä¹ĭéĹ´çļĦèģĶç³»
    0.07
    ิà¸ķร
    0.07
    sent
    0.07
    Activations Density 0.000%

    No Known Activations