© 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. 19110
    Prev
    Next
    INDEX
    Explanations

    wave propagation

    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
    /apt
    -0.07
     lashes
    -0.06
    éĴĪ对
    -0.06
     stem
    -0.06
    èº
    -0.06
    åłĨ
    -0.06
    èĴ¸çħ®
    -0.06
    침
    -0.06
    yyy
    -0.06
     Nights
    -0.06
    POSITIVE LOGITS
     propagation
    0.11
    Propagation
    0.11
     propagate
    0.10
     propagated
    0.09
     travelling
    0.09
     propag
    0.09
     impulse
    0.09
    ä¼łæĴŃ
    0.09
    +xml
    0.09
    _delay
    0.08
    Activations Density 0.004%

    No Known Activations