© 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. 20044
    Prev
    Next
    INDEX
    Explanations

    (?<=(?:testlist\b)|(?:){)})

    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
    ney
    -0.05
     unknown
    -0.05
     die
    -0.05
    äºĨ对
    -0.05
     den
    -0.05
    æĹ©
    -0.05
     bell
    -0.05
    ies
    -0.05
     smooth
    -0.05
    éĹ´çļĦ
    -0.04
    POSITIVE LOGITS
     chau
    0.07
    endor
    0.07
    ergus
    0.06
     mè
    0.06
     fek
    0.06
     Ùħباش
    0.06
    кеÑĢ
    0.06
    кеÑĢа
    0.06
    hu
    0.06
    çļĦä¸ĢåĿĹ
    0.06
    Activations Density 0.003%

    No Known Activations