© 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. 18192
    Prev
    Next
    INDEX
    Explanations

    medical patients or specimens

    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
    rowned
    -0.06
    à¹ģà¸Ł
    -0.06
    eldom
    -0.06
    aded
    -0.06
    atory
    -0.05
     seguido
    -0.05
    Locator
    -0.05
    quisite
    -0.05
    εÏħ
    -0.05
    êµIJ
    -0.05
    POSITIVE LOGITS
    è¯Ĩ
    0.06
    iscos
    0.06
    edBy
    0.05
     geler
    0.05
    ÃŃd
    0.05
     Sanity
    0.05
     quar
    0.05
    IMER
    0.05
    å¹³
    0.05
    纨
    0.05
    Activations Density 0.001%

    No Known Activations