© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6590
    Prev
    Next
    INDEX
    Explanations

    chic, stylish, trendy, sophisticated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纵横
    -0.09
    lot
    -0.08
    çļĸ
    -0.08
    Extended
    -0.08
    éĴ³
    -0.08
    ä¸įéĶĻçļĦ
    -0.08
    çĩĥçħ¤
    -0.08
    é¦Ķ
    -0.08
    æīĭ游
    -0.08
    èĤīç±»
    -0.08
    POSITIVE LOGITS
    æŶå°ļ
    0.15
    æ°Ķè´¨
    0.14
    é£İæł¼
    0.14
    åĵģä½į
    0.13
     chic
    0.13
     stylish
    0.12
    ä¼ĺéĽħ
    0.12
    style
    0.12
     ÑģÑĤилÑĮ
    0.12
    åħ¸éĽħ
    0.11
    Activations Density 0.127%

    No Known Activations