© 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. 20928
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    rá
    -0.07
     today
    -0.07
    ukat
    -0.07
    intas
    -0.07
    ä»Ĭ天
    -0.07
    èĩªåı¤
    -0.07
    plast
    -0.07
    çݰ代çļĦ
    -0.07
    ekom
    -0.07
    today
    -0.06
    POSITIVE LOGITS
    0.06
    -
    0.06
    ally
    0.05
    èįIJ
    0.05
     had
    0.05
    oly
    0.05
    èģļ
    0.05
     (
    0.04
     major
    0.04
    æĮī
    0.04
    Activations Density 0.015%

    No Known Activations