© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 320
    Prev
    Next
    INDEX
    Explanations

    code and technical 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
    ;!
    -0.35
     èĭ¥è¦ģ
    -0.34
    oriously
    -0.34
    ðŁĵIJ
    -0.33
    /MPL
    -0.32
    âļĹ
    -0.32
     GANG
    -0.32
    ]={↵
    -0.31
     PÃ¥
    -0.31
    -League
    -0.30
    POSITIVE LOGITS
     at
    0.27
     in
    0.26
     also
    0.25
     ifdef
    0.24
     of
    0.23
     –
    0.23
    ,
    0.23
     and
    0.23
    0.22
     -
    0.22
    Activations Density 1.755%

    No Known Activations