© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    stadiums, halls, and ball games

    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
    _DEFIN
    -0.10
    ç²¾
    -0.09
    enstein
    -0.09
    å±ĬæŶ
    -0.08
    ÙħÙĪÙĨ
    -0.08
    çĭIJ
    -0.08
    大åѸ
    -0.08
    åĬłæ²¹ç«Ļ
    -0.08
    éĺħåİĨ
    -0.08
    ermen
    -0.08
    POSITIVE LOGITS
    é²ľè¡Ģ
    0.11
    ç½ļ
    0.11
    undle
    0.10
     thumbs
    0.09
    yers
    0.09
    thumbs
    0.09
    æ³£
    0.09
    人身
    0.09
    ATUS
    0.08
    zial
    0.08
    Activations Density 0.007%

    No Known Activations