© 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. 18452
    Prev
    Next
    INDEX
    Explanations

    step, 2

    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
     ám
    -0.06
    oster
    -0.06
    æ»ļ
    -0.06
     medie
    -0.06
    endu
    -0.05
    inarie
    -0.05
    éĴ±çļĦ
    -0.05
    à¸Īิà¸Ļ
    -0.05
    panse
    -0.05
    basic
    -0.05
    POSITIVE LOGITS
    phem
    0.06
    åįĬ
    0.05
    aeda
    0.05
    اط
    0.05
    æĿ¡
    0.05
    acro
    0.05
    erial
    0.05
    umd
    0.05
    اصÙĦ
    0.05
    å°¤åħ¶æĺ¯
    0.05
    Activations Density 0.003%

    No Known Activations