© 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. 19302
    Prev
    Next
    INDEX
    Explanations

    head

    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
    ;!
    -0.06
    ély
    -0.06
    compiled
    -0.06
    éģ¥éģ¥
    -0.06
    åı©
    -0.06
    virt
    -0.06
    alore
    -0.06
    üst
    -0.06
    elapsed
    -0.05
    æ¸Ī
    -0.05
    POSITIVE LOGITS
    æł¹
    0.05
    اÛĮت
    0.05
    aker
    0.05
     Pro
    0.05
    bs
    0.05
    æĢ
    0.05
     product
    0.05
    é£İæł¼çļĦ
    0.05
    ritz
    0.05
    ps
    0.05
    Activations Density 0.001%

    No Known Activations