© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17699
    Prev
    Next
    INDEX
    Explanations

    religious figures and expressions

    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
    èĦij
    -0.07
     brain
    -0.06
     heart
    -0.06
    core
    -0.06
    áĥ¯
    -0.06
     core
    -0.06
     Brain
    -0.05
    骨干
    -0.05
     intime
    -0.05
     Core
    -0.05
    POSITIVE LOGITS
     mòn
    0.06
     defer
    0.06
    对ä¸Ĭ
    0.05
    rego
    0.05
    两ä½į
    0.05
    omba
    0.05
    èĵĦ
    0.05
    emas
    0.05
    aszt
    0.05
     ожида
    0.05
    Activations Density 0.037%

    No Known Activations