© 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. 18038
    Prev
    Next
    INDEX
    Explanations

    spoken out

    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
    éģ®
    -0.05
    пли
    -0.05
     Ø®ÙĦ
    -0.05
    åŁºçĤ¹
    -0.05
    çĤ¸
    -0.05
     coup
    -0.05
    æķ·
    -0.05
    åľ¨æĪijåĽ½
    -0.05
    rio
    -0.05
    okrat
    -0.05
    POSITIVE LOGITS
    ë§ĪìŀIJ
    0.06
    abor
    0.06
     ÑĥÑĤÑĢа
    0.06
    gether
    0.06
     Barnett
    0.06
    OfWork
    0.06
    ature
    0.06
    åĪĺæĸĩ
    0.06
    ogli
    0.06
    å½¢å¼ıå¤ļæł·
    0.06
    Activations Density 0.006%

    No Known Activations