© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    linking verbs and common words

    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
    ä¸įçľĭ
    -0.09
    ä¸įä»İ
    -0.08
    ä¸įåıª
    -0.08
     ìķĦ무리
    -0.08
    orrent
    -0.08
    ä¸įè°Ī
    -0.07
     compag
    -0.07
    ture
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    ope
    -0.07
    POSITIVE LOGITS
     ones
    0.10
     наобоÑĢоÑĤ
    0.10
     something
    0.08
     anzi
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
    ä»Ģä¹Īåij¢
    0.07
     вÑģего
    0.07
    缸åıį
    0.07
    æľīèĩªå·±çļĦ
    0.07
     simply
    0.07
    Activations Density 0.048%

    No Known Activations