© 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. 1648
    Prev
    Next
    INDEX
    Explanations

    entities and titles

    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
     ×Ķ×ķ×ĵ
    -0.20
     cuck
    -0.20
    åºij
    -0.19
    âĺķ
    -0.18
     stalk
    -0.18
    suming
    -0.18
    æłijæŀĿ
    -0.18
     semiclass
    -0.18
    èĭ¡
    -0.18
    undefined
    -0.18
    POSITIVE LOGITS
     :";↵
    0.23
    /↵↵↵↵
    0.22
    ridged
    0.21
    htmlspecialchars
    0.21
    æĶ¹
    0.21
     Geschä
    0.21
    presso
    0.20
     embod
    0.20
    >{!!
    0.20
    åģķ
    0.20
    Activations Density 0.001%

    No Known Activations