© 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-CHAT-65K
    7. 46350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    craper
    -0.28
     italiane
    -0.27
    GNUC
    -0.25
    crap
    -0.25
     CAUSED
    -0.24
     gratuite
    -0.23
    ncy
    -0.23
    AFX
    -0.23
    =";↵
    -0.23
     Pics
    -0.23
    POSITIVE LOGITS
    æ¸ħåĩĢ
    0.22
     compareTo
    0.21
     flo
    0.21
     ><?
    0.20
     Universal
    0.20
    0.20
    èįĩ
    0.20
     plaque
    0.20
    0
    0.19
    çłĶåıij
    0.19
    Activations Density 0.000%

    No Known Activations