© 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. 27434
    Prev
    Next
    INDEX
    Explanations

    probability indicating words

    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
    éĢļ常æĺ¯
    -0.10
    usually
    -0.10
    å¾Ģå¾Ģæĺ¯
    -0.10
    å¾Ģå¾Ģ
    -0.09
    å¾Ģå¾Ģä¼ļ
    -0.09
     usually
    -0.09
     biasanya
    -0.09
     عادة
    -0.09
    åı¯ä¸įæĺ¯
    -0.09
    å¸ĮæľĽåı¯ä»¥
    -0.09
    POSITIVE LOGITS
     possibly
    0.08
    èĩ³å°ijåľ¨
    0.08
    haps
    0.08
    possibly
    0.08
     someday
    0.07
    ä¸įä¹ħçļĦå°ĨæĿ¥
    0.07
     future
    0.07
     somewhere
    0.07
    èĩ³å°ij
    0.07
    ä½Ĩ缮åīį
    0.07
    Activations Density 1.012%

    No Known Activations