© 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. 29044
    Prev
    Next
    INDEX
    Explanations

    different entities or aspects

    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
    æ±Ľ
    -0.08
    è§Ħæł¼
    -0.08
    гоÑĢа
    -0.08
    ADER
    -0.07
    ÏĩÏī
    -0.07
    å°¤åħ¶æĺ¯
    -0.07
    ÖĦ
    -0.07
     inutil
    -0.07
    ifix
    -0.07
    ungan
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮç±»åŀĭçļĦ
    0.12
    ä¸įåIJĮçļĦ
    0.11
    æĪªçĦ¶ä¸įåIJĮçļĦ
    0.11
     respectively
    0.10
    æľīä¸įåIJĮçļĦ
    0.10
    ä¸įåIJĮçļĦ人
    0.10
     differently
    0.09
    åĪĨåĪ«æĺ¯
    0.09
     different
    0.09
    æĪªçĦ¶ä¸įåIJĮ
    0.09
    Activations Density 0.088%

    No Known Activations