© 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. 2830
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    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
    1
    -0.38
    2
    -0.36
    0
    -0.36
    3
    -0.35
    4
    -0.32
    5
    -0.32
    9
    -0.32
    8
    -0.31
    6
    -0.30
     draped
    -0.30
    POSITIVE LOGITS
    __;
    0.43
    âĸ·
    0.42
     *))
    0.40
     èĭ¥è¦ģ
    0.38
    NCY
    0.38
    uckland
    0.35
    ï¹¢
    0.35
     ×Ķ×ķ×ĵ
    0.34
    âĨĹ
    0.34
    ãĢĥ
    0.34
    Activations Density 3.280%

    No Known Activations