© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    ending suffix "ing" or foreign characters

    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
    igner
    -0.09
    bject
    -0.09
    ãģ¾ãģ¾
    -0.09
    elling
    -0.09
    ÑĪний
    -0.09
    ption
    -0.08
    ught
    -0.08
    å°Ķå¤ļ
    -0.08
    BJECT
    -0.08
    ç»ıä¿¡
    -0.08
    POSITIVE LOGITS
    ãĥ¥ãĥ¼
    0.09
    lyph
    0.08
    oes
    0.08
    ROUP
    0.08
    -mort
    0.08
    благо
    0.08
    纶
    0.08
    ä¸įè¡°
    0.08
    igsaw
    0.07
    ural
    0.07
    Activations Density 0.005%

    No Known Activations