© 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. 18789
    Prev
    Next
    INDEX
    Explanations

    medical/technical terms and 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
    éŨä¸ĭ
    -0.06
     Desta
    -0.05
    arez
    -0.05
    гÑĸд
    -0.05
     tros
    -0.05
     chau
    -0.05
     tô
    -0.05
    vr
    -0.05
     бÑĥдÑĮ
    -0.05
    æ¯ıä¸Ģ个è§ĴèIJ½
    -0.05
    POSITIVE LOGITS
    fee
    0.06
    åħ·
    0.06
    kunde
    0.05
    iew
    0.05
    atoio
    0.05
    ÙĪاÙħ
    0.05
     Fee
    0.05
    po
    0.05
    çĦļ
    0.05
    ħ
    0.05
    Activations Density 0.075%

    No Known Activations