© 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. 36854
    Prev
    Next
    INDEX
    Explanations

    sports team names

    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
    笼
    -0.09
    仪
    -0.09
    æł·åŃIJ
    -0.08
     sugar
    -0.08
    åĥı个
    -0.08
    stitial
    -0.08
    西äºļ
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
    天çĦ¶
    -0.08
    æĸ°ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    utable
    0.11
    owie
    0.10
    éĨĭ
    0.09
    Ñĥни
    0.09
    bsite
    0.09
     MCU
    0.09
    EXIT
    0.08
     Nguy
    0.08
    irs
    0.08
    èĪŁ
    0.08
    Activations Density 0.030%

    No Known Activations