© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2834
    Prev
    Next
    INDEX
    Explanations

    former or future

    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
     optim
    -0.07
     ëĨ
    -0.06
    并ä¸įçŁ¥éģĵ
    -0.06
     unint
    -0.06
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    à¯ģவ
    -0.06
    åĪļåĪļå¼Ģå§ĭ
    -0.06
    icie
    -0.06
     intuit
    -0.06
    hev
    -0.06
    POSITIVE LOGITS
    _presence
    0.08
    ëį°
    0.08
    å¥¢æľĽ
    0.08
    åıijçĶŁäºİ
    0.08
    bidden
    0.07
    大è§Ħ模çļĦ
    0.07
    estre
    0.07
    åĪĹ为
    0.07
    æĺ¯å¾Īå¤ļ
    0.07
    ä¸įå±ŀäºİ
    0.07
    Activations Density 0.015%

    No Known Activations