© 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. 19421
    Prev
    Next
    INDEX
    Explanations

    if not, but, maybe

    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
    ductory
    -0.06
    eiro
    -0.06
    äºĨä¸Ģ
    -0.06
    æĽľ
    -0.06
    ouce
    -0.06
    ä¹ĭæĢ¥
    -0.06
    ezu
    -0.06
     probabilmente
    -0.06
    è¦Ĩ
    -0.06
    opensource
    -0.06
    POSITIVE LOGITS
    å¤ĦçļĦ
    0.05
    undry
    0.05
    aste
    0.05
    pty
    0.05
    ast
    0.05
    ort
    0.05
    os
    0.05
    å¦Ĥæŀľæĺ¯
    0.05
    èĻķçļĦ
    0.05
    ole
    0.05
    Activations Density 0.010%

    No Known Activations