© 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. 22044
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    pond
    -0.06
     gener
    -0.05
    ä¾Ŀ
    -0.05
     ìļ°
    -0.05
    och
    -0.05
     chy
    -0.05
    ÙħÙĨ
    -0.05
    hoe
    -0.05
    çĭĤ
    -0.05
    éĻĦ
    -0.05
    POSITIVE LOGITS
    ãĥĸãĥª
    0.06
    å±Ģå±Ģéķ¿
    0.06
    çł¥
    0.06
    对ç«ĭ
    0.05
     gegens
    0.05
     aborted
    0.05
     หมืà¹Īà¸Ļ
    0.05
     experience
    0.05
    åħ³éŨ
    0.05
    Äįaj
    0.05
    Activations Density 0.002%

    No Known Activations