© 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. 14070
    Prev
    Next
    INDEX
    Explanations

    dehydro / hydroxylase / lyase / olefination

    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
    带åĽŀ
    -0.08
    магни
    -0.07
    è¸ıå®ŀ
    -0.07
     brought
    -0.07
    noc
    -0.07
    .intersection
    -0.07
     mau
    -0.07
    sci
    -0.07
     Oval
    -0.07
    èµĭåĢ¼
    -0.07
    POSITIVE LOGITS
    .escape
    0.09
    dehy
    0.08
    å½¢æĪIJ
    0.08
    .NewRequest
    0.08
    aho
    0.08
    并形æĪIJ
    0.08
     libert
    0.07
     terbentuk
    0.07
    å½¢æĪIJä¸Ģ个
    0.07
     Bard
    0.07
    Activations Density 0.006%

    No Known Activations