© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1190
    Prev
    Next
    INDEX
    Explanations

    disclaimer and license

    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
    vably
    -0.31
    .Gray
    -0.31
    avanaugh
    -0.29
    bilit
    -0.28
    ç½ijé¦ĸ页
    -0.27
     Posté
    -0.27
    доб
    -0.26
    )((((
    -0.26
    ROID
    -0.25
    uguay
    -0.25
    POSITIVE LOGITS
    avenport
    0.45
    ainty
    0.37
    ilogy
    0.33
    asename
    0.33
    arcy
    0.28
    uncan
    0.27
    exterity
    0.27
    isoft
    0.26
    ownt
    0.25
    .parseDouble
    0.24
    Activations Density 4.981%

    No Known Activations