© 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. 20910
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
    å®£ä¼łåij¨
    -0.06
    adesh
    -0.06
    usat
    -0.06
    elay
    -0.06
    åĮ»éĻ¢è¿Ľè¡Į
    -0.06
    estone
    -0.06
    atically
    -0.06
    issement
    -0.06
    aits
    -0.06
     célé
    -0.06
    POSITIVE LOGITS
     regard
    0.05
    è¨ĺ
    0.05
    èľĢ
    0.05
     men
    0.05
    大æ¦Ĥ
    0.05
    0.05
    æĹłå½¢
    0.05
    arge
    0.05
     pro
    0.05
    arg
    0.05
    Activations Density 0.012%

    No Known Activations