© 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. 25835
    Prev
    Next
    INDEX
    Explanations

    rearrangement, isomerization, redistribution

    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
    anko
    -0.08
    åĹĵ
    -0.08
    ceived
    -0.07
    ourced
    -0.07
    ackers
    -0.07
    æĿİåĺī
    -0.07
    ä¸įæĶ¾
    -0.07
     séqu
    -0.07
    ×¢
    -0.07
    arking
    -0.07
    POSITIVE LOGITS
     resh
    0.09
    åıijçĶŁåľ¨
    0.08
    æĿ¥å¾ĹåıĬ
    0.08
    ton
    0.07
     occured
    0.07
     occur
    0.07
    转åĮĸ
    0.07
    åĪ°åħ¶ä»ĸ
    0.07
    åıijçĶŁåIJİ
    0.07
     mediated
    0.07
    Activations Density 0.022%

    No Known Activations