© 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. 17757
    Prev
    Next
    INDEX
    Explanations

    research and study

    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
    ao
    -0.06
    ali
    -0.06
     eth
    -0.05
    aut
    -0.05
    -0.05
     pr
    -0.05
     appropriately
    -0.05
    ân
    -0.05
    mio
    -0.04
     aut
    -0.04
    POSITIVE LOGITS
    iette
    0.07
    wykle
    0.07
    éĻ¸
    0.07
    habil
    0.07
    intégration
    0.07
    ietta
    0.06
    Ä±ÅŁÄ±
    0.06
    à¹īà¸Ńย
    0.06
    quil
    0.06
    verse
    0.06
    Activations Density 0.069%

    No Known Activations