© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    gas, liquid, and waste mixtures containing substances

    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
    åĬ±
    -0.07
    OBO
    -0.07
    à¸ŀัà¸ļ
    -0.07
    .outer
    -0.07
    æŀ¶è®¾
    -0.07
    ë§Įíģ¼
    -0.07
     configurable
    -0.07
    uml
    -0.07
    åįĥåįĥ
    -0.07
    ürg
    -0.06
    POSITIVE LOGITS
     containing
    0.16
    ä¸ŃåIJ«æľī
    0.15
     contains
    0.15
     contain
    0.15
     chứa
    0.14
    contains
    0.14
    åIJ«æľī
    0.14
     Contains
    0.13
     contenant
    0.13
    Contains
    0.12
    Activations Density 0.224%

    No Known Activations