© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    technical topics

    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
    .BackgroundImage
    -0.23
    çļĦ带é¢Ĩ
    -0.21
    BufferData
    -0.20
     tú
    -0.19
    ';";↵
    -0.19
    å¹´ä¹ĭä¹ħ
    -0.19
    aux
    -0.18
    galement
    -0.18
    empt
    -0.18
    ÃŃcia
    -0.18
    POSITIVE LOGITS
    (@"%@",
    0.28
     <!--[
    0.23
    ;;;;;;;;
    0.22
     Oczy
    0.21
    entiful
    0.21
    :".$
    0.20
    ocide
    0.19
    åİŁæĸĩåľ°åĿĢ
    0.19
     bergen
    0.19
     )↵↵↵↵↵↵↵↵
    0.19
    Activations Density 0.001%

    No Known Activations