© 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. 22520
    Prev
    Next
    INDEX
    Explanations

    multiple, single, or one instance/item

    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
    à¸Ĺà¸Ńà¸Ķ
    -0.06
    lyn
    -0.06
    림
    -0.05
    ilo
    -0.05
    éħª
    -0.05
    çĦ¶
    -0.05
    æĭŁ
    -0.05
    奥å°Ķ
    -0.05
    æ³¥
    -0.05
    initi
    -0.05
    POSITIVE LOGITS
    åd
    0.07
    å¤©æľº
    0.06
    cre
    0.06
    ibro
    0.06
    ivist
    0.06
    åĪĨ享çļĦ
    0.06
    -write
    0.06
    ä»Ķç»Ĩçľĭ
    0.06
    rohr
    0.05
    icter
    0.05
    Activations Density 0.044%

    No Known Activations