© 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. 17583
    Prev
    Next
    INDEX
    Explanations

    health, specific medical conditions, concepts, and related topics

    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
    nes
    -0.05
    ingles
    -0.05
    大å®ĹåķĨåĵģ
    -0.05
    æѦæĺĮ
    -0.05
     именно
    -0.05
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.05
     zasi
    -0.05
    azor
    -0.05
    olos
    -0.05
     mist
    -0.05
    POSITIVE LOGITS
    èĩĤ
    0.06
    å¯Į
    0.06
    ärm
    0.06
    wohl
    0.05
    -ci
    0.05
    plant
    0.05
    管æīĢ
    0.05
    oute
    0.05
    schied
    0.05
    èĪį
    0.05
    Activations Density 0.064%

    No Known Activations