© 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. 31694
    Prev
    Next
    INDEX
    Explanations

    compared to or higher than

    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
    iron
    -0.07
     Rov
    -0.07
    ond
    -0.07
    lh
    -0.07
    bara
    -0.07
    urna
    -0.06
    mongo
    -0.06
    bur
    -0.06
    æĪijæĺ¯ä¸ª
    -0.06
    çĶ±åŃ¦æł¡
    -0.06
    POSITIVE LOGITS
     compared
    0.17
    缸è¾ĥäºİ
    0.17
    缸æ¯Ķ
    0.15
    ä¸įåIJĮäºİ
    0.15
    缸è¾ĥ
    0.15
     Compared
    0.15
    缸æ¯Ķäºİ
    0.15
    åĮºåĪ«äºİ
    0.14
     dibandingkan
    0.14
    ä¸įåĥı
    0.13
    Activations Density 0.448%

    No Known Activations