© 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. 19851
    Prev
    Next
    INDEX
    Explanations

    food and drink names

    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
    ä¼ļåIJİ
    -0.06
    host
    -0.06
    çĿ
    -0.05
    airs
    -0.05
    raga
    -0.05
    éĢĥ
    -0.05
     sight
    -0.05
    ¿
    -0.05
    赦
    -0.05
    á»ı
    -0.05
    POSITIVE LOGITS
    och
    0.06
     Pum
    0.06
    aman
    0.05
     ades
    0.05
    åķ¸
    0.05
    ç¯ł
    0.05
    cking
    0.05
    ç«ĭå¾·
    0.05
    éŨå¸Ĥ
    0.05
    osc
    0.05
    Activations Density 0.001%

    No Known Activations