© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16696
    Prev
    Next
    INDEX
    Explanations

    wake up

    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
    Negative Logits
    sé
    -0.05
    eleg
    -0.05
    fruit
    -0.05
    elem
    -0.05
    egg
    -0.05
    forme
    -0.05
    ç»ĵæŀľæĺ¯
    -0.05
    arb
    -0.05
    ç²¾ç¥ŀä¸Ĭ
    -0.05
    {}]
    -0.05
    POSITIVE LOGITS
    æĿ¥ä¹ĭ
    0.07
    nant
    0.07
    unya
    0.06
    éĵ¿
    0.06
    оÑģÑĮ
    0.06
    usable
    0.06
    ative
    0.06
    ustr
    0.06
    åī§
    0.06
    kog
    0.06
    Activations Density 0.003%

    No Known Activations