© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20466
    Prev
    Next
    INDEX
    Explanations

    increase or reduction

    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
    ä¸įè¯Ĩ
    -0.06
     Ñģоз
    -0.05
    æ°Ľ
    -0.05
    .utc
    -0.05
     вм
    -0.05
    ä¸Ģ缴éĥ½æĺ¯
    -0.05
    ä»Ĺ
    -0.05
    æĺ¯ä»Ģä¹Īæł·
    -0.05
    æĺ¯åIJ¦
    -0.05
    åºĶæł¹æį®
    -0.04
    POSITIVE LOGITS
    otis
    0.07
    å¢Ĺ
    0.06
    oren
    0.06
    å¢ŀåĬłçļĦ
    0.06
    åĬłçļĦ
    0.06
    дÑĢоб
    0.06
    ington
    0.06
    é¡»æıIJä¾Ľ
    0.06
    '](
    0.06
    plen
    0.06
    Activations Density 0.025%

    No Known Activations