© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21297
    Prev
    Next
    INDEX
    Explanations

    food and drink quality

    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
    afil
    -0.11
    ढ
    -0.09
     меÑĢ
    -0.09
     Contributors
    -0.09
    .cgi
    -0.08
    åħ¨ç¨ĭ
    -0.08
    åºĶ该å¦Ĥä½ķ
    -0.08
    illac
    -0.08
    hell
    -0.08
    DBC
    -0.08
    POSITIVE LOGITS
    è´¨éĩıåĴĮ
    0.11
     quality
    0.10
    ç§įç±»
    0.10
    åĴĮæľįåĬ¡
    0.09
    å¼Ģä¸ļ
    0.09
    ä¹Łä¸įéĶĻ
    0.09
    館
    0.08
    errs
    0.08
    滨
    0.08
    èѦåĬ¡
    0.08
    Activations Density 0.031%

    No Known Activations