© 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. 46229
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    estroy
    -0.33
    oproject
    -0.31
     Erotic
    -0.31
    abox
    -0.31
    Indented
    -0.30
    icter
    -0.29
    roys
    -0.29
    -await
    -0.29
    rawer
    -0.28
    iginal
    -0.28
    POSITIVE LOGITS
    主åŁİåĮº
    0.24
    é¦ij
    0.23
    er
    0.22
     essentially
    0.21
    ç»Ĵ
    0.20
    就好äºĨ
    0.20
    ist
    0.20
     startPosition
    0.20
    寺åºĻ
    0.19
    ing
    0.19
    Activations Density 0.002%

    No Known Activations