© 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. 3327
    Prev
    Next
    INDEX
    Explanations

    naming or defining

    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
    .UseVisualStyleBackColor
    -0.23
    oksen
    -0.19
     (~(
    -0.19
     @}
    -0.19
    raits
    -0.19
    lineno
    -0.19
    estation
    -0.19
    icorn
    -0.19
    RIORITY
    -0.19
    egasus
    -0.18
    POSITIVE LOGITS
     called
    1.02
    åı«åģļ
    1.00
    称为
    0.98
    称ä¹ĭ为
    0.90
    called
    0.90
    åı«
    0.84
     Called
    0.83
    被称为
    0.82
    Called
    0.75
     termed
    0.73
    Activations Density 1.761%

    No Known Activations