© 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. 27259
    Prev
    Next
    INDEX
    Explanations

    isotopic labeling and incorporation

    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
     Vak
    -0.08
    ç±»ä¸ĵä¸ļ
    -0.07
    aturity
    -0.07
    çīĪæĿĥçŃī
    -0.07
    commend
    -0.07
    éric
    -0.07
    ectes
    -0.07
     unga
    -0.07
    ä¸Ģ空
    -0.07
     aangeb
    -0.07
    POSITIVE LOGITS
     tracer
    0.07
    交æį¢
    0.07
     exchanges
    0.07
     tracing
    0.07
    tracer
    0.07
    -tag
    0.07
     обога
    0.07
     exchange
    0.07
    追踪
    0.07
     traced
    0.07
    Activations Density 0.061%

    No Known Activations