© 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. 57593
    Prev
    Next
    INDEX
    Explanations

    code comments and notices

    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
    и
    -0.13
    ਼
    -0.13
    ÙĬ
    -0.12
    iog
    -0.11
    à±į
    -0.11
    ing
    -0.11
    iha
    -0.10
    ÑģмоÑĤÑĢиÑĤе
    -0.10
    ами
    -0.10
    tures
    -0.10
    POSITIVE LOGITS
    áĢ¸
    0.12
    Ø©
    0.12
    ä¸Ģ个
    0.11
    gether
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.11
    Ùĩ
    0.10
    ÙĦ
    0.10
    Ñı
    0.10
    ed
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    Activations Density 0.078%

    No Known Activations