© 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. 136
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    ))?
    -0.24
    inston
    -0.23
    ppelin
    -0.22
    éparation
    -0.22
    anged
    -0.22
    (Cs
    -0.22
    etus
    -0.22
    iring
    -0.21
    ?option
    -0.21
    ailer
    -0.20
    POSITIVE LOGITS
    strtolower
    0.24
     ofApp
    0.24
    hood
    0.21
    usband
    0.19
    æĽ²
    0.19
    our
    0.19
    绿
    0.19
    fwrite
    0.19
    (
    0.18
    aryawan
    0.18
    Activations Density 0.001%

    No Known Activations