© 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. 46209
    Prev
    Next
    INDEX
    Explanations

    order and sequence

    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
    traîn
    -0.22
    .Accessible
    -0.20
    omid
    -0.20
     flexGrow
    -0.20
    çħ³
    -0.20
    mobx
    -0.19
    Boundary
    -0.19
    SingleOrDefault
    -0.18
    WithMany
    -0.18
    èĩ¾
    -0.18
    POSITIVE LOGITS
    ster
    0.24
    ade
    0.22
    æ±
    0.21
    detalle
    0.21
    inous
    0.19
    gnore
    0.19
    าศ
    0.19
    XY
    0.19
    AGMA
    0.19
    åĨį
    0.19
    Activations Density 0.050%

    No Known Activations