© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    from the start

    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
    次äºİ
    -0.08
    åĽºæľī
    -0.07
    à¹Ģà¸ŀ
    -0.07
     POLL
    -0.07
    —are
    -0.07
     unkompl
    -0.07
    åĨ¥
    -0.07
    åĿĽ
    -0.06
     tqdm
    -0.06
    оÑĢе
    -0.06
    POSITIVE LOGITS
    è¿ĻæŶ
    0.16
    è¿Ļç§įæĥħåĨµä¸ĭ
    0.15
    è¿ĻæŶåĢĻ
    0.13
    æѤæŶ
    0.13
    éĤ£æŶ
    0.13
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.12
    è¿ĻæŶçļĦ
    0.12
    éĢĻæĻĤ
    0.11
    è¿Ļç§įæĥħåĨµ
    0.11
    æѤæŶçļĦ
    0.11
    Activations Density 0.018%

    No Known Activations