© 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. 18325
    Prev
    Next
    INDEX
    Explanations

    dating, reconstruction, forest, boiler, Christmas, snowshoes, vaccine, Silver Eagle, server

    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
    ç»Ŀèī²
    -0.06
    вани
    -0.06
    obbled
    -0.06
     пÑĥнк
    -0.06
    uhl
    -0.06
    æĺ¯ä»Ģä¹Īæł·
    -0.06
    建议使çĶ¨
    -0.06
     jewel
    -0.06
    entos
    -0.06
    ease
    -0.05
    POSITIVE LOGITS
    Ïį
    0.05
     successful
    0.05
    l
    0.05
    iri
    0.05
    æĵ¦
    0.05
    羣缸
    0.05
    eti
    0.05
    åIJĪæ³ķ
    0.05
    la
    0.05
    åŃĶæĺİ
    0.05
    Activations Density 0.118%

    No Known Activations