© 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. 21165
    Prev
    Next
    INDEX
    Explanations

    special or formatting characters

    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
    好åij¢
    -0.07
    åħ·
    -0.06
     personn
    -0.06
     ÎĨ
    -0.06
    å¨Ĩ
    -0.06
    ä¸ĭæŀ¶
    -0.06
    æĺ¯ä»Ģä¹Īåij¢
    -0.06
    érir
    -0.06
    Ùĩر
    -0.06
    pris
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.06
     omitted
    0.06
    ;
    0.05
     omit
    0.05
    çľģçķ¥
    0.05
    Compiled
    0.05
     rep
    0.05
     "
    0.05
    太å¤ļ
    0.05
     minor
    0.05
    Activations Density 0.125%

    No Known Activations