© 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. 29723
    Prev
    Next
    INDEX
    Explanations

    membrane, gel, piezoelectric

    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
    aint
    -0.08
    aira
    -0.07
    ä¿±è¿Ľ
    -0.07
    omma
    -0.06
    è¿Ļæł·åı¯ä»¥
    -0.06
    olit
    -0.06
    请ä¸ĭè½½
    -0.06
    ×ł×¡
    -0.06
    nei
    -0.06
    ôs
    -0.06
    POSITIVE LOGITS
    ilty
    0.08
    ])-
    0.08
    Into
    0.08
    åIJĦç§įä¸įåIJĮçļĦ
    0.07
    lingen
    0.07
     Into
    0.07
     genannte
    0.07
    anty
    0.07
    imate
    0.07
    ingo
    0.07
    Activations Density 0.178%

    No Known Activations