© 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. 18598
    Prev
    Next
    INDEX
    Explanations

    medical conditions and disorders

    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
    æľīä½Ļ
    -0.06
    ana
    -0.06
    jang
    -0.06
    ä¸Ĭå®ĺ
    -0.06
    rophe
    -0.06
    agers
    -0.06
    åįłæĢ»
    -0.05
    icarakan
    -0.05
    anim
    -0.05
    zuk
    -0.05
    POSITIVE LOGITS
    umann
    0.05
    ä¸įåIJĪæł¼
    0.05
    olin
    0.05
    runs
    0.05
     fas
    0.05
     varietÃł
    0.05
     schw
    0.05
    ược
    0.05
     excuse
    0.05
    exposition
    0.05
    Activations Density 0.016%

    No Known Activations