© 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. 46024
    Prev
    Next
    INDEX
    Explanations

    transition words

    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
     ancest
    -0.23
     baño
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
     sublicense
    -0.20
    íĶĦë¡ľê·¸
    -0.20
    /******/
    -0.20
    NSMutableDictionary
    -0.19
    ie
    -0.19
    entiful
    -0.19
     tako
    -0.18
    POSITIVE LOGITS
    èĩ³äºİ
    0.78
    èĩ³æĸ¼
    0.53
     Regarding
    0.48
    Regarding
    0.46
     regarding
    0.44
    åħ³äºİ
    0.40
    èĢĮ对äºİ
    0.39
     èĩ
    0.36
     concerning
    0.34
     meanwhile
    0.28
    Activations Density 0.156%

    No Known Activations