© 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. 17748
    Prev
    Next
    INDEX
    Explanations

    natural products extraction

    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
    çŁ³å¢¨
    -0.08
    isen
    -0.07
    æ°´æĺŁ
    -0.07
    ahul
    -0.07
    éķĢ
    -0.07
    phant
    -0.07
    æĿıèĬ±
    -0.07
    åĩ¡äºĭ
    -0.07
    é³
    -0.07
    adius
    -0.07
    POSITIVE LOGITS
     extracts
    0.13
    æıIJåıĸçī©
    0.12
     extract
    0.12
    æıIJåıĸ
    0.11
     medicinal
    0.11
     extraction
    0.10
    extract
    0.10
    æıIJçĤ¼
    0.09
     Extract
    0.09
    ä¸ŃæıIJåıĸ
    0.09
    Activations Density 0.245%

    No Known Activations