© 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. 45854
    Prev
    Next
    INDEX
    Explanations

    enzymes

    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
    quete
    -0.23
    ().'/
    -0.22
    imenti
    -0.22
    TOTYPE
    -0.21
    autoload
    -0.20
    çĸ´
    -0.20
    .BASELINE
    -0.20
    ESSAGES
    -0.20
    modo
    -0.19
     indeb
    -0.19
    POSITIVE LOGITS
    éħ¶
    0.26
     enzymes
    0.24
     enzyme
    0.23
    æ´»æĢ§
    0.22
    ThanOrEqualTo
    0.21
     activity
    0.21
    addtogroup
    0.20
    enzyme
    0.20
    .scalablytyped
    0.20
    æ´»åĬĽ
    0.19
    Activations Density 0.009%

    No Known Activations