© 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. 26017
    Prev
    Next
    INDEX
    Explanations

    recurrence

    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
     sepat
    -0.08
    ysh
    -0.07
    èĩĬ
    -0.07
     available
    -0.07
    .story
    -0.07
     nhục
    -0.07
     Lives
    -0.07
    AndWait
    -0.07
    bach
    -0.06
    åĩºæīĭ
    -0.06
    POSITIVE LOGITS
    ä»įçĦ¶åŃĺåľ¨
    0.13
    ä»įåŃĺåľ¨
    0.13
    åĨį度
    0.12
    ä»įæľī
    0.12
    ä»įéľĢ
    0.12
    ä¾ĿçĦ¶åŃĺåľ¨
    0.12
    è¿ĺæĺ¯ä¼ļ
    0.12
    ä»įçĦ¶
    0.11
    ä»įå°Ĩ
    0.11
    å¤įåıij
    0.10
    Activations Density 0.204%

    No Known Activations