© 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. 2693
    Prev
    Next
    INDEX
    Explanations

    anti

    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
    -Trump
    -0.28
    !=(
    -0.28
     ilma
    -0.24
    oliday
    -0.23
    egov
    -0.21
    ngr
    -0.21
    eled
    -0.21
    forcements
    -0.21
     avalia
    -0.21
    aeda
    -0.21
    POSITIVE LOGITS
     CircularProgress
    0.26
    åĵĤ
    0.23
     Geschäfts
    0.21
    ISMATCH
    0.20
     \%
    0.20
     {[
    0.20
    èģĥ
    0.20
     når
    0.19
     hvis
    0.19
    akin
    0.19
    Activations Density 0.116%

    No Known Activations