© 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. 16966
    Prev
    Next
    INDEX
    Explanations

    numbers and equations

    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
    ä½Ļ份
    -0.06
     اÙĦجÙĦ
    -0.06
    lemn
    -0.06
    çĿĢæĪijçļĦ
    -0.06
    rena
    -0.06
    Siamo
    -0.05
    parate
    -0.05
    ijľ
    -0.05
    িà¦ķà§įষ
    -0.05
     reconstruction
    -0.05
    POSITIVE LOGITS
    鸦
    0.06
     definit
    0.06
     Veg
    0.06
    ä¸Ģå¤ľ
    0.06
    æĹłéļľç¢į
    0.05
    ureen
    0.05
    camp
    0.05
    èIJ¥
    0.05
    缴
    0.05
     Correa
    0.05
    Activations Density 0.112%

    No Known Activations