© 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. 182
    Prev
    Next
    INDEX
    Explanations

    medical terms

    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
    娱ä¹IJå¹³åı°
    -0.21
     maç
    -0.20
     xhttp
    -0.18
    娱ä¹IJåľº
    -0.17
    æį¢åı¥è¯Ŀ
    -0.17
     Rencontres
    -0.16
     ArtÃŃculo
    -0.16
    è¿ĺ以为
    -0.15
    شدد
    -0.15
    åıĸåĨ³
    -0.15
    POSITIVE LOGITS
    benh
    0.21
    Ulus
    0.20
    'icon
    0.19
    -Trump
    0.19
    âļĹ
    0.19
    对åħ¶çľŁå®ŀ
    0.19
    æľīçļĦçݩ家
    0.19
    åįĥæĸ¹çĻ¾
    0.19
    ðŁĵIJ
    0.18
    foundland
    0.18
    Activations Density 98.412%

    No Known Activations