© 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. 19594
    Prev
    Next
    INDEX
    Explanations

    reading or loading files

    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
    idd
    -0.06
    ä½ľçī©
    -0.05
    æĢ»æ¯Ķ
    -0.05
    åijĬè¯īä½ł
    -0.05
    a
    -0.05
    ab
    -0.05
    åħ¬æľī
    -0.05
    dd
    -0.05
     sexes
    -0.05
    -sized
    -0.05
    POSITIVE LOGITS
    yrı
    0.06
    eam
    0.06
    masuk
    0.06
    æ¨
    0.06
    plays
    0.06
     scouting
    0.06
    elry
    0.06
    isit
    0.06
    logging
    0.06
    ettings
    0.06
    Activations Density 0.002%

    No Known Activations