© 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. 485
    Prev
    Next
    INDEX
    Explanations

    overall tendencies

    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
    #ga
    -0.27
    iage
    -0.26
     disappe
    -0.24
    illery
    -0.24
    ËĤ
    -0.24
    curacy
    -0.23
    ibri
    -0.23
     earthqu
    -0.22
    âĭĨ
    -0.22
    redi
    -0.21
    POSITIVE LOGITS
     overall
    0.35
    æĺİæĺ¾
    0.31
     consistently
    0.29
    æĢ»ä½ĵ
    0.28
     Overall
    0.28
    overall
    0.27
    æķ´ä½ĵ
    0.26
     except
    0.26
     almost
    0.26
    Overall
    0.25
    Activations Density 2.637%

    No Known Activations