© 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. 20448
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or color codes

    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
    ertime
    -0.07
    å±±åİ¿
    -0.07
    etto
    -0.07
    ault
    -0.06
    Pts
    -0.06
    ÙĪÙī
    -0.06
    /gtest
    -0.06
    ignon
    -0.06
    åij¨åĪ°
    -0.06
    åı£æľį液
    -0.06
    POSITIVE LOGITS
    dech
    0.07
    æľīèī²
    0.07
    OTES
    0.07
    Ø°Ùİا
    0.06
    åIJĥåIJĥ
    0.06
    å°Ĩå°±
    0.06
    è´¤
    0.06
    otÄĻ
    0.06
    æŁĵ
    0.06
    <\/
    0.06
    Activations Density 0.018%

    No Known Activations