© 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. 18443
    Prev
    Next
    INDEX
    Explanations

    enzyme activity or synthesis

    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
    ikli
    -0.09
    okus
    -0.09
    å®ŀä¹łæľŁéĹ´
    -0.08
    ucer
    -0.08
    åIJĮäºĭ们
    -0.08
    èĮĹ
    -0.07
    usan
    -0.07
    oku
    -0.07
    icule
    -0.07
    å·¥ä½ľèĢħçļĦ
    -0.07
    POSITIVE LOGITS
    åħ³éĶ®çݯèĬĤ
    0.11
    çݯèĬĤ
    0.10
    çĵ¶é¢Ī
    0.09
    çݯèĬĤçļĦ
    0.09
     bott
    0.08
     bottleneck
    0.08
    éĺ»å¡ŀ
    0.08
    åħ³éĶ®
    0.08
    çݯèĬĤä¸Ń
    0.08
    åłµå¡ŀ
    0.08
    Activations Density 0.051%

    No Known Activations