© 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. 18222
    Prev
    Next
    INDEX
    Explanations

    for [tokens related to reasons, time, people]

    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
    ergestellt
    -0.07
    å©Ĩ
    -0.06
    äºİå¿ĥ
    -0.06
    å½¢çļĦ
    -0.06
    ä¼Ĺå¤ļ
    -0.06
    λλον
    -0.06
    inat
    -0.06
    rosoft
    -0.05
    водÑı
    -0.05
    plied
    -0.05
    POSITIVE LOGITS
    اذ
    0.05
    æ®ĸ
    0.05
    ander
    0.05
    ../../../
    0.05
    ito
    0.05
    =o
    0.05
    åĪĨä¹ĭä¸Ģ
    0.05
    oret
    0.05
    æĢĢéĩĮ
    0.05
     whether
    0.05
    Activations Density 0.040%

    No Known Activations