© 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. 18999
    Prev
    Next
    INDEX
    Explanations

    player or character entities

    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
    è¿ĩæŶ
    -0.05
     Sense
    -0.05
     Paren
    -0.05
    int
    -0.05
    adesh
    -0.05
     sense
    -0.05
    ä¸Ģ说
    -0.05
    icien
    -0.05
    essen
    -0.05
     sen
    -0.05
    POSITIVE LOGITS
    quat
    0.07
    urance
    0.06
    brand
    0.06
    为ä»Ģä¹Īåij¢
    0.06
    ÃŃnc
    0.06
    èĺij
    0.06
    quÃŃ
    0.06
    管çIJĨæīĢ
    0.06
    yanto
    0.05
    åħį
    0.05
    Activations Density 0.004%

    No Known Activations