© 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. 16919
    Prev
    Next
    INDEX
    Explanations

    animal production and veterinary medicine

    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
    å¿į
    -0.06
    ä¸ĢæŀĿ
    -0.06
    æĭĤ
    -0.06
    èķĬ
    -0.06
    åľ°ä¸ĭ
    -0.06
    omed
    -0.06
    åĩıçģ¾
    -0.05
    ATTERN
    -0.05
    _pattern
    -0.05
    ajakan
    -0.05
    POSITIVE LOGITS
    пло
    0.06
    /questions
    0.06
    overn
    0.05
     slaughter
    0.05
    instead
    0.05
     kenn
    0.05
     fict
    0.05
     Sim
    0.05
     Black
    0.05
    åij¨åħ¨
    0.05
    Activations Density 0.091%

    No Known Activations