© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    take

    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
    vince
    -0.23
    weeted
    -0.23
    ouce
    -0.22
    eor
    -0.21
    redient
    -0.21
    Ļ¨
    -0.21
    elerik
    -0.20
    readcr
    -0.20
     Depths
    -0.20
    oproject
    -0.19
    POSITIVE LOGITS
     advantage
    0.40
     care
    0.28
     refuge
    0.26
    byss
    0.25
     steps
    0.25
     ÑĥÑĩаÑģÑĤие
    0.24
    .RadioButton
    0.24
    ðŁĵĬ
    0.24
     note
    0.24
    elsea
    0.23
    Activations Density 0.443%

    No Known Activations