© 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. 46038
    Prev
    Next
    INDEX
    Explanations

    discussing subjects

    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
    oriously
    -0.23
     Prostit
    -0.23
    eworthy
    -0.22
    .TryParse
    -0.22
    athing
    -0.21
    )test
    -0.21
    -Jul
    -0.21
    æĭľå¸ĪåѦ
    -0.21
    #######↵
    -0.20
     CascadeType
    -0.20
    POSITIVE LOGITS
    0.22
    <Renderer
    0.21
    ridor
    0.21
     overclock
    0.20
    åįŁ
    0.20
    çī¹åĪ«
    0.20
     '
    0.20
    enville
    0.19
     neither
    0.19
    åı£åı·
    0.19
    Activations Density 1.467%

    No Known Activations