© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    air quality and pollution

    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
    æĿµ
    -0.10
     Chill
    -0.09
    æľ¨
    -0.09
    _TLS
    -0.09
    举æĸ¹
    -0.09
    IRR
    -0.08
     TRE
    -0.08
    éĵķ
    -0.08
    ante
    -0.08
    马
    -0.08
    POSITIVE LOGITS
    空æ°Ķè´¨éĩı
    0.11
    è¿ĩ滤
    0.10
    空æ°Ķ
    0.10
    ç²¹
    0.10
    æ±ļ
    0.10
    èĤ®
    0.10
    寡
    0.10
     quality
    0.10
    åĵģè´¨
    0.10
    çĺª
    0.10
    Activations Density 0.086%

    No Known Activations