© 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. 21511
    Prev
    Next
    INDEX
    Explanations

    italian and italy

    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
    Ø©
    -0.06
    yah
    -0.06
     Taschen
    -0.06
    ijker
    -0.06
    ÑĩаÑĤки
    -0.06
    irectional
    -0.06
    διά
    -0.06
    cato
    -0.06
    etsy
    -0.06
    ä½ĵéĩı
    -0.06
    POSITIVE LOGITS
    uing
    0.06
    unid
    0.06
    aten
    0.05
    uron
    0.05
    opl
    0.05
    обе
    0.05
    fant
    0.05
    à¹Ģà¸ļ
    0.05
    ãģĹãģ¾ãģĨ
    0.05
    /english
    0.05
    Activations Density 0.016%

    No Known Activations