© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20444
    Prev
    Next
    INDEX
    Explanations

    carbonylative cyclization coupling reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ~
    -0.06
    å½¢æĢģ
    -0.05
    åĮĸæĪIJ
    -0.05
    water
    -0.05
    åİŁçĶŁ
    -0.05
    è°Ī
    -0.05
    å½¢æĪIJ
    -0.05
    -form
    -0.05
    -water
    -0.05
    ta
    -0.05
    POSITIVE LOGITS
    écur
    0.07
    althy
    0.07
    aszt
    0.07
    irurg
    0.07
    ä¹IJä¹İ
    0.07
    assem
    0.07
     incontourn
    0.07
    ierno
    0.07
    elenium
    0.06
    راÙħ
    0.06
    Activations Density 0.013%

    No Known Activations