© 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. 20774
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
     ahor
    -0.06
    l
    -0.06
    overn
    -0.05
    znacz
    -0.05
    indle
    -0.05
    kim
    -0.05
    og
    -0.05
    inkel
    -0.05
    fore
    -0.05
    inda
    -0.05
    POSITIVE LOGITS
     .**
    0.06
    enhagen
    0.06
    åħģ
    0.06
     Gda
    0.06
    oldem
    0.05
    ÙĪÙĦÙĪج
    0.05
    çIJ¥
    0.05
    odont
    0.05
    æĿ¥ä¹ĭ
    0.05
    åīįè¡ĮçļĦ
    0.05
    Activations Density 0.265%

    No Known Activations