© 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. 18769
    Prev
    Next
    INDEX
    Explanations

    dressed in clothing

    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
    ed
    -0.06
    å¾Ī
    -0.05
    pec
    -0.05
    almost
    -0.05
    2
    -0.05
    edan
    -0.05
    7
    -0.05
    ìŀħ
    -0.05
    abd
    -0.05
     {
    -0.05
    POSITIVE LOGITS
    à¸ģาย
    0.07
    kki
    0.07
    à¹īา
    0.06
    betul
    0.06
    venuto
    0.06
    ÙĨÚ¯
    0.06
    Ñıн
    0.06
    /or
    0.06
    ingatkan
    0.06
    æĹ¥ä¸Ĭ
    0.06
    Activations Density 0.002%

    No Known Activations