© 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. 20807
    Prev
    Next
    INDEX
    Explanations

    electron transport and phosphorylation

    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
    wear
    -0.06
    èµIJ
    -0.06
    è³ľ
    -0.06
     countless
    -0.05
     habit
    -0.05
    ersp
    -0.05
    æĭ¥æĬ±
    -0.05
     dissolution
    -0.05
    亿ä¸ĩ
    -0.05
    erno
    -0.05
    POSITIVE LOGITS
    imismo
    0.06
     Ùħدار
    0.06
    æĬĢæľ¯æĢ§
    0.05
    Ø·ÙĦ
    0.05
     Nielsen
    0.05
    ninger
    0.05
    äºĮè¦ģ
    0.05
    seud
    0.05
    æĢ»çļĦ
    0.05
    ederal
    0.05
    Activations Density 0.017%

    No Known Activations