© 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. 23245
    Prev
    Next
    INDEX
    Explanations

    corporate registries

    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
    ÛĮÙĦ
    -0.07
    æķĻæĪij
    -0.07
    å®ŀçİ°ä¸Ńåįİæ°ijæĹıä¼Łå¤§å¤įåħ´
    -0.07
    æĨ§
    -0.07
    è§ģæĪij
    -0.06
    .fm
    -0.06
    ahu
    -0.06
    ionato
    -0.06
    ippo
    -0.06
    è¨Ĺ
    -0.06
    POSITIVE LOGITS
    ä¼Ĭæĸ¯
    0.07
    .lbl
    0.07
    Cancelled
    0.07
    zionalitÃł
    0.07
    XmlElement
    0.07
    plusplus
    0.06
     оÑĩеÑĢед
    0.06
    коле
    0.06
    ç¢į
    0.06
     hinges
    0.06
    Activations Density 0.187%

    No Known Activations