© 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. 18299
    Prev
    Next
    INDEX
    Explanations

    installation commands

    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
    اÙĨÙĩ
    -0.07
    å¿ĥæĤ¦
    -0.06
     buc
    -0.06
    æĢ§å¼º
    -0.05
    undle
    -0.05
     subl
    -0.05
     dili
    -0.05
    究åħ¶åİŁåĽł
    -0.05
    pliant
    -0.05
    é¦Ĩ
    -0.05
    POSITIVE LOGITS
    å°ıå°ı
    0.05
    -mort
    0.05
    tter
    0.05
    è¦ģåģļ
    0.05
    ÑİÑĢа
    0.05
    enom
    0.05
    æīĢä½ľ
    0.05
    ä¸ŀ
    0.05
    èijĹçļĦ
    0.05
     fÃŃsico
    0.05
    Activations Density 0.015%

    No Known Activations