© 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. 27538
    Prev
    Next
    INDEX
    Explanations

    each [token]

    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
    äºĨä¸ĢåĪĩ
    -0.09
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.09
     altogether
    -0.08
    ä¸ĢåĪĩçļĦ
    -0.08
    两çĶ¨
    -0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.08
    æĺ¯ä¸ĢåĪĩ
    -0.08
    ä¸Ģ举
    -0.08
    è¿Ļä¸ĢåĪĩ
    -0.08
    manos
    -0.08
    POSITIVE LOGITS
    åIJĦèĩª
    0.15
    åIJĦèĩªçļĦ
    0.14
     respective
    0.13
     individually
    0.12
     jeweils
    0.12
    ìĶ©
    0.12
    åIJĦæľī
    0.11
     câte
    0.11
    ãģļãģ¤
    0.11
     jeweilige
    0.11
    Activations Density 0.273%

    No Known Activations