© 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. 64317
    Prev
    Next
    INDEX
    Explanations

    propagation or spreading

    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
    æĤ¬
    -0.07
    çī¹åĪ«å¤ļ
    -0.07
    èĦĸåŃIJ
    -0.07
    /logging
    -0.07
    itan
    -0.07
    pts
    -0.07
    access
    -0.06
    夫åŃIJ
    -0.06
    临éŨ
    -0.06
    contri
    -0.06
    POSITIVE LOGITS
     propagation
    0.12
    ä¼łæĴŃ
    0.12
     propagate
    0.11
     propag
    0.11
    Propagation
    0.10
     fastest
    0.10
    çļĦéĢŁåº¦
    0.10
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.09
     spreading
    0.09
     Å¡ÃŃ
    0.09
    Activations Density 0.030%

    No Known Activations