© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3859
    Prev
    Next
    INDEX
    Explanations

    medical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    "url
    -0.22
     Redistribution
    -0.21
    	↵	↵↵
    -0.20
    ={"/
    -0.20
     ^=
    -0.18
    注å®ļ
    -0.18
    ÑĨиалÑĮн
    -0.18
     ?>&
    -0.18
    olated
    -0.18
    arrants
    -0.18
    POSITIVE LOGITS
    lev
    0.21
     hann
    0.21
    ï½ŀ↵↵
    0.21
    IJľ
    0.20
    <=(
    0.20
    èĪĨ
    0.20
    ç½ijé¦ĸ页
    0.19
    defgroup
    0.19
    addtogroup
    0.18
    resden
    0.18
    Activations Density 0.001%

    No Known Activations