© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22508
    Prev
    Next
    INDEX
    Explanations

    field names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     chans
    -0.06
    åħ³éĹŃçªĹåı£
    -0.06
     dikutip
    -0.06
    éĿ¢åĢĴ
    -0.06
    agre
    -0.06
    ÙĪÙĩ
    -0.06
     welt
    -0.06
     gyr
    -0.06
    дий
    -0.06
    å±¥èģĮ尽责
    -0.06
    POSITIVE LOGITS
    ail
    0.05
    èĩ£
    0.05
    0.05
    é¢ĦçķĻ
    0.05
    ÑĮÑİ
    0.05
    ÑĮев
    0.05
    lu
    0.05
     optional
    0.05
     empire
    0.05
    ical
    0.04
    Activations Density 0.014%

    No Known Activations