© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19703
    Prev
    Next
    INDEX
    Explanations

    together with

    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
    iert
    -0.06
    ird
    -0.06
    å®ļçļĦ
    -0.05
    æŁ¥å®ŀ
    -0.05
    ä¸įéľĢè¦ģ
    -0.05
    este
    -0.05
    /devices
    -0.05
    cert
    -0.05
    oner
    -0.05
    coord
    -0.05
    POSITIVE LOGITS
    ification
    0.06
    åľĨ满èIJ½å¹ķ
    0.06
    UIL
    0.06
    undet
    0.06
    ÙĦÙģ
    0.05
     selanjutnya
    0.05
    –and
    0.05
    รว
    0.05
    żeÅĦ
    0.05
    icity
    0.05
    Activations Density 0.001%

    No Known Activations