© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    court documents

    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
    :'',
    -0.21
     Ngo
    -0.21
    brahim
    -0.21
    findFirst
    -0.21
     Waterproof
    -0.21
    oriously
    -0.20
    ubbo
    -0.20
     Rolled
    -0.20
     Basement
    -0.19
    /*****************************************************************************↵
    -0.19
    POSITIVE LOGITS
    (targetEntity
    0.21
    .contentMode
    0.20
    nqu
    0.20
    .sax
    0.19
    unction
    0.19
    .raises
    0.19
    å¦Ĥæŀľçݩ家
    0.19
    åĤĻ
    0.19
    åĨįçİ°
    0.19
    ünst
    0.18
    Activations Density 0.024%

    No Known Activations