© 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. 20594
    Prev
    Next
    INDEX
    Explanations

    bit sizes (32, 64)

    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
    loff
    -0.06
    ebo
    -0.06
    flan
    -0.06
     ÙĪاÙĦÙħر
    -0.06
    ä¹ħä¹ĭ
    -0.06
    æ±Ĥæĺ¯
    -0.06
     Conce
    -0.06
    æľĪä¸Ĭ
    -0.06
    apon
    -0.05
     rig
    -0.05
    POSITIVE LOGITS
    ÑģÑĤÑĥ
    0.05
    grup
    0.05
    å¼ı
    0.05
    端起
    0.05
     stadig
    0.05
    è¿ĺæĺ¯ä¸Ģ个
    0.05
     copyrights
    0.05
    existe
    0.05
     оÑĤноÑģи
    0.05
    å¼ıä¸Ń
    0.05
    Activations Density 0.018%

    No Known Activations