© 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. 45935
    Prev
    Next
    INDEX
    Explanations

    do

    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/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
    intégr
    -0.26
    ">ÃĹ</
    -0.23
     окÑĢÑĥжаÑİÑī
    -0.22
    indsight
    -0.22
    dictions
    -0.22
    byss
    -0.22
    âĺŀ
    -0.21
     AndAlso
    -0.21
    rons
    -0.21
    bable
    -0.20
    POSITIVE LOGITS
     burge
    0.29
     handicap
    0.20
     however
    0.20
    ERSIST
    0.19
     décidé
    0.19
     deltaX
    0.19
    0.18
    ICTURE
    0.18
     réussi
    0.18
    æľīä¸Ģ
    0.18
    Activations Density 0.015%

    No Known Activations