© 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. 17239
    Prev
    Next
    INDEX
    Explanations

    days and months

    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
    empor
    -0.06
    ric
    -0.05
    ä¼ĺåĬ£
    -0.05
    íĥĦ
    -0.05
    æĺ¯ä¸įèĥ½
    -0.05
    then
    -0.05
    åħµé©¬ä¿ij
    -0.05
    iples
    -0.05
    atur
    -0.05
    ä¸įæ±Ĥ
    -0.05
    POSITIVE LOGITS
    åı·æĸĩ件
    0.05
    umpy
    0.05
     lao
    0.05
    ä¸ĢçĤ¹çĤ¹
    0.05
    echa
    0.05
     increment
    0.05
    ôn
    0.05
    eringen
    0.05
    åij¼å£°
    0.05
    é¹ıé£ŀ
    0.05
    Activations Density 0.006%

    No Known Activations