© 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. 399
    Prev
    Next
    INDEX
    Explanations

    formatting tags

    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
    alborg
    -0.27
    -scalable
    -0.26
    grily
    -0.23
     OMAP
    -0.23
    clusão
    -0.22
    åħ³äºİæĪij们
    -0.21
     ${({
    -0.21
    Reusable
    -0.21
     componentDidUpdate
    -0.21
    家éĥ½çŁ¥éģĵ
    -0.20
    POSITIVE LOGITS
    tá
    0.24
    ieme
    0.23
    usercontent
    0.22
    []{↵
    0.20
    IENTATION
    0.20
    mployee
    0.20
    cstdio
    0.19
    @yahoo
    0.19
    vincial
    0.19
    cassert
    0.19
    Activations Density 1.392%

    No Known Activations