© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18625
    Prev
    Next
    INDEX
    Explanations

    mathematical variables

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Franç
    -0.05
    inning
    -0.05
    구
    -0.05
    该项
    -0.05
    armed
    -0.05
    ergic
    -0.05
    av
    -0.05
     times
    -0.05
    ÑĥÑģка
    -0.05
    说ä¸Ģä¸ĭ
    -0.05
    POSITIVE LOGITS
    agne
    0.06
    #=
    0.06
    uche
    0.06
    ILD
    0.05
    ãģĿãĤīãģı
    0.05
    ại
    0.05
    ä¼ģä¸ļåħ³ç³»
    0.05
    uben
    0.05
    éĩĮéĿ¢æľī
    0.05
    кен
    0.05
    Activations Density 0.130%

    No Known Activations