© 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. 18043
    Prev
    Next
    INDEX
    Explanations

    tax advantages, destination, fiscal

    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
    wap
    -0.07
     abon
    -0.06
    漪
    -0.05
    cha
    -0.05
    åĮĿ
    -0.05
     Daily
    -0.05
    kut
    -0.05
     hag
    -0.05
    ãĥĬãĥ¼
    -0.05
     homes
    -0.05
    POSITIVE LOGITS
     terce
    0.07
    íĥģ
    0.07
    éħįå¥Ĺ
    0.06
    olu
    0.06
     atract
    0.06
    éĢīæĭ©åľ¨
    0.06
    å¼ķèµĦ
    0.06
     attrac
    0.06
    ä¸īåı·
    0.06
    æľĢéģ©
    0.06
    Activations Density 0.021%

    No Known Activations