© 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. 292
    Prev
    Next
    INDEX
    Explanations

    title

    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
    .moveToNext
    -0.24
     ++)↵
    -0.23
    Hôtel
    -0.22
     èĭ¥è¦ģ
    -0.21
    __;↵
    -0.20
    .repaint
    -0.20
    ceipt
    -0.20
    èĤ¼
    -0.20
     Wiring
    -0.19
     Unblock
    -0.19
    POSITIVE LOGITS
    ...</
    0.36
    -</
    0.29
     </
    0.27
    ,</
    0.26
    ittel
    0.25
    +</
    0.23
    aleigh
    0.23
     will
    0.23
    /*↵
    0.23
    }}</
    0.22
    Activations Density 0.457%

    No Known Activations