© 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. 18659
    Prev
    Next
    INDEX
    Explanations

    JSON structure or code syntax

    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
     dijal
    -0.06
    对æĤ¨
    -0.06
    对ä¸Ń
    -0.06
     dita
    -0.06
    pets
    -0.06
     congrat
    -0.05
    usine
    -0.05
    è³ĩéĩij
    -0.05
    ç»Ļ大家æݨèįIJ
    -0.05
     redd
    -0.05
    POSITIVE LOGITS
    ities
    0.06
    icity
    0.06
    çĹ´
    0.06
    !important
    0.05
    缮çļĦæĺ¯
    0.05
    缮çļĦ
    0.05
    iveness
    0.05
    ake
    0.05
    è¿ĩ硬
    0.05
    æĪIJçĨŁçļĦ
    0.05
    Activations Density 0.003%

    No Known Activations