© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    Acts of Congress

    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
    ,Th
    -0.25
    ,application
    -0.24
    åºĶæĶ¶è´¦
    -0.23
    ÙħØŃÙħد
    -0.22
    ,");↵
    -0.21
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
    subcategory
    -0.20
     ×Ķ×ķ×ĵ
    -0.20
    åĹIJ
    -0.20
    issen
    -0.20
    POSITIVE LOGITS
    unt
    0.20
     componentName
    0.20
    æĪijå½ĵæŶ
    0.20
    æ³ķæ¡Ī
    0.19
    .hasMore
    0.19
     surgeon
    0.19
    ABCDEFGHI
    0.19
    涿
    0.19
    Forget
    0.18
    æľĢåIJİä¸Ģ次
    0.18
    Activations Density 0.079%

    No Known Activations