© 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. 19156
    Prev
    Next
    INDEX
    Explanations

    French royalty and history

    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
    ónimo
    -0.07
    ÃŃsk
    -0.06
    çŁŃ
    -0.06
    çŁŃåı¥
    -0.06
    ledge
    -0.06
    ferred
    -0.06
    Åį
    -0.06
    ä¸Ń继
    -0.06
    ä¿ĿæĮģ
    -0.06
    å¾ĹæĦı
    -0.06
    POSITIVE LOGITS
    odi
    0.05
    å¦ĤçĥŁ
    0.05
     reform
    0.05
     fó
    0.05
    解å¼Ģ
    0.05
    åĪ¨
    0.05
     fol
    0.05
     pasi
    0.05
    pain
    0.05
     Schwar
    0.05
    Activations Density 0.002%

    No Known Activations