© 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. 18069
    Prev
    Next
    INDEX
    Explanations

    nationalities and groups

    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
    éĻIJ
    -0.06
    æ±Ĥ
    -0.06
    amaz
    -0.06
    atat
    -0.06
    为çĶŁ
    -0.05
    çĶŁ
    -0.05
    æĸ°é«ĺ
    -0.05
    anders
    -0.05
    pires
    -0.05
    letcher
    -0.05
    POSITIVE LOGITS
     ÑĤоже
    0.08
     ebenfalls
    0.07
    ç¼ĸè¾ijæݨèįIJ
    0.06
    à¸Ńีà¸ģà¸Ķà¹īวย
    0.06
    ä½łåij¢
    0.05
    æīĢè¦ģ
    0.05
    éļ±
    0.05
     ê²½ìļ°ëıĦ
    0.05
    ..."
    0.05
    ä¹Łå·²ç»ı
    0.05
    Activations Density 0.120%

    No Known Activations