© 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. 18434
    Prev
    Next
    INDEX
    Explanations

    ave

    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
    aga
    -0.06
    éĹ´æİ¥
    -0.06
    åİĤ
    -0.06
    st
    -0.05
    ÑĨ
    -0.05
    تر
    -0.05
    fec
    -0.05
    eros
    -0.05
     si
    -0.05
    anti
    -0.05
    POSITIVE LOGITS
    管æīĢ
    0.06
    äºĨä¸Ģå®ļ
    0.06
    -too
    0.06
    NIS
    0.06
    ä¸Ģ个æĸ°çļĦ
    0.06
    oba
    0.06
    urop
    0.06
    究
    0.05
    åĤ¢
    0.05
    继ç»Ń沿
    0.05
    Activations Density 0.001%

    No Known Activations