© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19645
    Prev
    Next
    INDEX
    Explanations

    ?

    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
    etak
    -0.06
     luni
    -0.05
    .lat
    -0.05
    ewn
    -0.05
    itzen
    -0.05
     crisis
    -0.05
    &
    -0.05
     order
    -0.05
    ekin
    -0.05
    央è§Ĩæĸ°éĹ»
    -0.04
    POSITIVE LOGITS
     primit
    0.07
    omat
    0.06
    istrator
    0.06
     midd
    0.06
    toff
    0.06
    anders
    0.06
    dez
    0.06
    eed
    0.06
    rza
    0.06
    spar
    0.06
    Activations Density 0.067%

    No Known Activations