© 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. 20459
    Prev
    Next
    INDEX
    Explanations

    ancient + civilizations/times/Greek/Chinese/forms

    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
    tros
    -0.07
    hô
    -0.06
    isons
    -0.06
    ütün
    -0.06
    åĢĻéĢī
    -0.06
    ordin
    -0.06
    æł·çļĦ
    -0.06
    cents
    -0.06
    ãĤ¹ãĥĨ
    -0.06
     thuáºŃn
    -0.06
    POSITIVE LOGITS
    ting
    0.06
    estic
    0.06
    ly
    0.06
    ech
    0.06
    etic
    0.06
    à¥į
    0.05
    zel
    0.05
    à¸Ħลาà¸ģร
    0.05
    ean
    0.05
    å¼Ģ好
    0.05
    Activations Density 0.004%

    No Known Activations