© 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. 45136
    Prev
    Next
    INDEX
    Explanations

    defined or depending

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ideally
    -0.08
     εγκα
    -0.07
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    -0.07
    abah
    -0.07
    agged
    -0.07
    ÑĢей
    -0.07
    ä¸įä¼ļæĺ¯
    -0.07
    çĦ¡çĸij
    -0.07
    åĨ°åĿĹ
    -0.07
    èĬ±å²Ĺ
    -0.07
    POSITIVE LOGITS
     differently
    0.10
    æľīä¸įåIJĮçļĦ
    0.09
    éĥ½æĬĬ
    0.09
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.09
     sometimes
    0.08
    è¿ĺæľīçļĦ
    0.08
     depending
    0.08
     different
    0.07
    ë§Īëĭ¤
    0.07
    æľīçļĦ
    0.07
    Activations Density 0.038%

    No Known Activations