© 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. 21429
    Prev
    Next
    INDEX
    Explanations

    perpetuates, perpetuation, perpetually

    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
    chy
    -0.08
    chol
    -0.08
    hti
    -0.08
    mien
    -0.07
    naz
    -0.07
    artes
    -0.07
    .Java
    -0.07
    ismic
    -0.07
    cez
    -0.07
    chos
    -0.07
    POSITIVE LOGITS
    ly
    0.06
    iously
    0.06
    0.05
    H
    0.05
    ä¸įæŃ¢
    0.04
    رÛĮاÙĨ
    0.04
    ÃŃ
    0.04
    1
    0.04
    imately
    0.04
     H
    0.04
    Activations Density 0.002%

    No Known Activations