© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    programming, await, try

    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
    .FindAsync
    -0.21
    :indexPath
    -0.20
    ecessarily
    -0.20
     bloginfo
    -0.19
    mie
    -0.19
    _idle
    -0.18
    æķ´çIJĨ
    -0.18
    ({_
    -0.18
    .EndsWith
    -0.18
     Raqqa
    -0.18
    POSITIVE LOGITS
    plet
    0.23
    ={"/
    0.23
    .assertRaises
    0.22
     Try
    0.22
    ,eg
    0.22
     try
    0.22
    try
    0.21
    ç»ĵæŀľ
    0.21
     Await
    0.21
    },č↵č↵
    0.21
    Activations Density 0.289%

    No Known Activations