© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19268
    Prev
    Next
    INDEX
    Explanations

    Olympic Games and related events

    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
    age
    -0.06
    wards
    -0.06
    ÄįÃŃ
    -0.06
    ittest
    -0.06
    itage
    -0.06
    accès
    -0.06
    urus
    -0.06
    itesse
    -0.06
    uem
    -0.05
    iley
    -0.05
    POSITIVE LOGITS
    ÑĢаÑĤно
    0.06
    sWith
    0.06
    plies
    0.05
    gars
    0.05
    æŀĿèĬ±
    0.05
    å¥ĭ
    0.05
    olars
    0.05
     Arbor
    0.05
    âĢĮ
    0.05
    éĺµ
    0.05
    Activations Density 0.016%

    No Known Activations