© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    separate or separately

    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
    yani
    -0.09
    etz
    -0.09
    çĻ»è®°è¯ģ
    -0.09
    çļĦéĥ½æĺ¯
    -0.08
    ìĹ´
    -0.08
    ombre
    -0.08
    à¸Īัà¸ĩ
    -0.08
     dần
    -0.08
    å¤§ä½ľ
    -0.08
    ä¸įåłª
    -0.07
    POSITIVE LOGITS
     separately
    0.17
     separate
    0.17
    åįķçĭ¬
    0.13
    çĭ¬ç«ĭ
    0.13
    çĭ¬ç«ĭçļĦ
    0.13
    åįķçĭ¬çļĦ
    0.12
     Separate
    0.12
     оÑĤделÑĮно
    0.11
     terpisah
    0.11
     seperate
    0.11
    Activations Density 0.074%

    No Known Activations