© 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. 19656
    Prev
    Next
    INDEX
    Explanations

    lists and 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
    веÑĢÑı
    -0.07
    ersh
    -0.06
    åıĻ
    -0.06
    trup
    -0.06
    注æĦı
    -0.06
    ridge
    -0.06
    -gay
    -0.06
    ellingen
    -0.06
    leps
    -0.06
    inely
    -0.06
    POSITIVE LOGITS
    st
    0.06
     lay
    0.05
     deposits
    0.05
    es
    0.05
     well
    0.05
     deposition
    0.05
     probably
    0.05
    apt
    0.04
    once
    0.04
     merit
    0.04
    Activations Density 0.026%

    No Known Activations