© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56876
    Prev
    Next
    INDEX
    Explanations

    electrical and physical components

    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
    ãĥ¼ãĥķ
    -0.08
    å¹²ç»Ĩèĥŀ
    -0.08
     docking
    -0.07
    大èĤł
    -0.07
    .bio
    -0.07
    çĺ¾
    -0.07
    éªĭ
    -0.07
     NIH
    -0.07
     Bradford
    -0.07
    骨
    -0.07
    POSITIVE LOGITS
    è¾ĵçĶµ
    0.10
    éħįçĶµ
    0.10
    ç»Ŀç¼ĺ
    0.09
    åıĺçĶµç«Ļ
    0.09
    çĶµèĥ½
    0.09
     transformer
    0.09
     transformers
    0.09
    带çĶµ
    0.09
    çĶµç¼Ĩ
    0.08
    åıĺåİĭåĻ¨
    0.08
    Activations Density 0.017%

    No Known Activations