© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21919
    Prev
    Next
    INDEX
    Explanations

    legal citations or code

    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
    èģļåIJĪçī©
    -0.06
    éŨåħ³
    -0.06
     berk
    -0.06
    å®Ĺ
    -0.06
    untas
    -0.06
    okok
    -0.06
     quyá»ģn
    -0.06
    åĪ°ä¸ŃåĽ½
    -0.06
    æ±ģ
    -0.06
    cycles
    -0.06
    POSITIVE LOGITS
    ente
    0.05
    èĽĻ
    0.05
    夹æĿĤ
    0.05
    alog
    0.05
     wherever
    0.05
    æľ¬äººåľ¨
    0.05
    éĽģ
    0.05
     ÑĥÑĤо
    0.04
    äººåľ¨
    0.04
    æĸ°åĬłåĿ¡
    0.04
    Activations Density 0.002%

    No Known Activations