© 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. 46263
    Prev
    Next
    INDEX
    Explanations

    later

    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
    .jd
    -0.19
    .dataTables
    -0.19
    ermann
    -0.19
    èŁĢ
    -0.19
    atori
    -0.19
    "text
    -0.19
    -Sah
    -0.18
    èĩ³ä¸Ĭ
    -0.18
    _REPEAT
    -0.18
    #End
    -0.18
    POSITIVE LOGITS
     later
    0.46
    æĪij们å°Ĩ
    0.42
    later
    0.41
    æĪij们è¦ģ
    0.39
    æĪij们éľĢè¦ģ
    0.35
     Later
    0.35
    Later
    0.34
    æĪij们çļĦ
    0.34
    aremos
    0.32
    åIJİç»Ń
    0.30
    Activations Density 0.272%

    No Known Activations