© 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. 60644
    Prev
    Next
    INDEX
    Explanations

    biotechnology, system, defect, proper nouns

    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
    è¿Ľä¸ĢæŃ¥æݨåĬ¨
    -0.06
    DT
    -0.06
    enner
    -0.06
    کا
    -0.06
    ساÙĨ
    -0.06
     Lands
    -0.06
    hung
    -0.06
    hen
    -0.06
    izen
    -0.06
    æľīåħ³
    -0.06
    POSITIVE LOGITS
     hingegen
    0.11
    åĪĻæĺ¯
    0.11
    åĪĻè¦ģ
    0.09
    åĪĻ为
    0.09
    åĪĻéľĢè¦ģ
    0.09
     dagegen
    0.09
    åīĩæĺ¯
    0.09
    åĪĻåı¯ä»¥
    0.09
    åĪĻä¼ļ
    0.09
    ä¸įéĤ£ä¹Ī
    0.08
    Activations Density 0.025%

    No Known Activations