© 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. 46098
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
    è®®äºĭ
    -0.23
    åĩ¡æľ¬ç½ij
    -0.20
    ern
    -0.20
     An
    -0.20
    æĹıèĩªæ²»
    -0.19
    æĹłè®ºæĺ¯åħ¶
    -0.19
    é²²
    -0.19
    éħIJ
    -0.19
     D
    -0.18
    çļĦèĦļæŃ¥
    -0.18
    POSITIVE LOGITS
    âļĹ
    0.25
    schlie
    0.24
    ]={↵
    0.23
    âĹĤ
    0.23
    byss
    0.23
    ãĦ§
    0.23
    ajes
    0.23
     cocci
    0.23
    gger
    0.22
    âĮĤ
    0.22
    Activations Density 0.074%

    No Known Activations