© 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. 20508
    Prev
    Next
    INDEX
    Explanations

    underlying mechanisms or connections

    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
    æĦıçļĦ
    -0.06
    elai
    -0.06
    izo
    -0.06
    ä¸Ģåĩ»
    -0.06
    nict
    -0.06
    yük
    -0.06
     sidelines
    -0.05
    ynchronized
    -0.05
    rimon
    -0.05
    ioned
    -0.05
    POSITIVE LOGITS
    hoff
    0.07
    jata
    0.07
    ation
    0.06
    kej
    0.06
    ations
    0.06
    plat
    0.05
     driven
    0.05
    kel
    0.05
    orgia
    0.05
    zal
    0.05
    Activations Density 0.006%

    No Known Activations