© 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. 17047
    Prev
    Next
    INDEX
    Explanations

    entrepreneurs, holiday, plus size, waiting

    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
    åĮĸ
    -0.06
    æĬ½
    -0.05
    -0.05
     t
    -0.05
    ç²¾
    -0.05
    d
    -0.05
     mé
    -0.05
    éĩĩ
    -0.04
     W
    -0.04
     mis
    -0.04
    POSITIVE LOGITS
    ä¸ªå·¥ä½ľ
    0.07
     anon
    0.07
    æ®ĩ
    0.06
     Viola
    0.06
    konfirmasi
    0.06
    ãĤªãĤ¹ãĤ¹ãĥ¡ãģ§ãģĻ
    0.06
    cest
    0.06
    ouston
    0.06
    ìĭ¸
    0.06
     Ente
    0.06
    Activations Density 0.150%

    No Known Activations