© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    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
    <src
    -0.23
    nilai
    -0.23
    -addons
    -0.21
    åı£æ°Ķ
    -0.20
    æ®ĥ
    -0.20
    cratch
    -0.20
    èĤĦ
    -0.20
    /popper
    -0.20
     scaleX
    -0.19
    çĸĸ
    -0.19
    POSITIVE LOGITS
    æĻ®éģįåŃĺåľ¨
    0.24
     SERIES
    0.21
     AssemblyDescription
    0.21
     defenseman
    0.20
    Generic
    0.20
    .Generic
    0.20
     Generic
    0.20
    èĦ±é¢ĸ
    0.19
    _generic
    0.19
    thood
    0.19
    Activations Density 0.304%

    No Known Activations