© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20244
    Prev
    Next
    INDEX
    Explanations

    drug ingredients and substances

    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
    adurch
    -0.07
    à¹Īาà¸Ļัà¹īà¸Ļ
    -0.06
    çijŀå®ī
    -0.06
    OPY
    -0.06
    aisia
    -0.06
     بÙĪت
    -0.06
    htm
    -0.06
    Spo
    -0.06
    ovem
    -0.06
    Ñĩайно
    -0.06
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.06
    lim
    0.06
    гоÑĤавли
    0.05
    m
    0.05
    ä
    0.05
    çªĿ
    0.05
    ong
    0.05
    anton
    0.05
    izz
    0.05
     prepar
    0.05
    Activations Density 0.002%

    No Known Activations