© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 3795
    Prev
    Next
    INDEX
    Explanations

    specific technical details

    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
    erÃł
    -0.20
    .AutoSizeMode
    -0.19
    	Spring
    -0.18
    ApplicationBuilder
    -0.18
    NewItem
    -0.18
    á»ļ
    -0.18
     neg
    -0.18
    eger
    -0.18
    å¹´ä¹ĭä¹ħ
    -0.18
    å°ıæĹ¶åīį
    -0.18
    POSITIVE LOGITS
    macen
    0.24
    âĦī
    0.22
    )./
    0.21
     '');
    0.20
    å®ł
    0.20
    enment
    0.20
     WrocÅĤaw
    0.20
    ));//
    0.20
     :";↵
    0.19
     RedirectTo
    0.19
    Activations Density 0.001%

    No Known Activations