© 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. 20260
    Prev
    Next
    INDEX
    Explanations

    number of countries

    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
     Grimm
    -0.05
    ä¸įä¹ı
    -0.05
    tle
    -0.05
    awn
    -0.05
    bug
    -0.05
    çĦ¶èĢĮ
    -0.05
    Ùĭ
    -0.05
    poss
    -0.05
    -0.05
    ä¾µçķ¥
    -0.04
    POSITIVE LOGITS
    ajs
    0.08
    chor
    0.07
    ocations
    0.06
    inten
    0.06
    ordi
    0.06
     **.**
    0.06
    æ»ļæ»ļ
    0.06
    มà¸Ļ
    0.06
    èĴ¸èĴ¸
    0.06
    veri
    0.06
    Activations Density 0.009%

    No Known Activations