© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21211
    Prev
    Next
    INDEX
    Explanations

    reading file or database data

    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
     Wis
    -0.05
    kunde
    -0.05
     repet
    -0.05
    ëĭ¤ê³ł
    -0.05
    woord
    -0.05
     ÑĢ
    -0.05
    ocratic
    -0.05
    med
    -0.05
    lined
    -0.05
     cuent
    -0.05
    POSITIVE LOGITS
    اÙģر
    0.06
    æīĢæľīçļĦ人
    0.06
     Repar
    0.06
    ItemList
    0.06
    ZEN
    0.06
     conforte
    0.06
    Ø©
    0.06
    szyscy
    0.06
    éĵł
    0.06
    æĹłä¸Ĭ
    0.06
    Activations Density 0.003%

    No Known Activations