© 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. 277
    Prev
    Next
    INDEX
    Explanations

    work

    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
    aukee
    -0.61
    KHTML
    -0.46
    pÅĤyw
    -0.44
    uxtap
    -0.37
    .AutoComplete
    -0.33
    @dynamic
    -0.32
     nuest
    -0.32
    niest
    -0.30
     misd
    -0.30
    herits
    -0.29
    POSITIVE LOGITS
    ylie
    0.31
    ASHINGTON
    0.27
    inston
    0.25
    iggins
    0.25
    obble
    0.24
    alendar
    0.23
    am
    0.23
    ysqli
    0.22
    èĹī
    0.22
    -ranging
    0.21
    Activations Density 3.329%

    No Known Activations