© 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. 18976
    Prev
    Next
    INDEX
    Explanations

    whose

    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
    観
    -0.06
    еме
    -0.06
    anci
    -0.06
    è¿ĺæĺ¯æľīäºĽ
    -0.05
    )$/
    -0.05
    orsz
    -0.05
    à¹Ģà¸ķà¸Ńรà¹Į
    -0.05
    æŃ¤ä¸º
    -0.05
    naud
    -0.05
    é¢ĺ为
    -0.05
    POSITIVE LOGITS
    alin
    0.05
    pli
    0.05
    oot
    0.05
    ogu
    0.05
    nat
    0.05
    ÑĪÑĤ
    0.05
     fort
    0.05
    имÑĥ
    0.05
     summed
    0.05
     eagerly
    0.05
    Activations Density 0.124%

    No Known Activations