© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    åĨħ马
    -0.23
    ++){↵↵
    -0.21
    ÐŀÐĿ
    -0.21
    InMillis
    -0.20
    å§Ķç»Ħç»ĩéĥ¨
    -0.19
    å§Ķå®£ä¼łéĥ¨
    -0.19
    's
    -0.19
    .handleError
    -0.19
    '
    -0.19
    ány
    -0.19
    POSITIVE LOGITS
    istrate
    0.25
    /MPL
    0.25
    .IsNullOr
    0.25
    /Dk
    0.25
    antry
    0.23
     Zus
    0.22
     âĵĺ
    0.22
    -License
    0.21
    /Gate
    0.21
    -anchor
    0.21
    Activations Density 0.837%

    No Known Activations