© 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. 8671
    Prev
    Next
    INDEX
    Explanations

    email address or link

    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
    ä»ĵ
    -0.09
    主æĦı
    -0.08
    éħª
    -0.08
    åľ¨æł¡
    -0.08
    磨
    -0.08
    _vs
    -0.08
    .grad
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    ä¸įå°ij
    -0.08
    麽
    -0.08
    POSITIVE LOGITS
    advert
    0.10
    ç¿ĺ
    0.09
    ç»ijæŀ¶
    0.08
    ilm
    0.08
    æīįèĥ½
    0.08
    èħĶ
    0.08
    æīįåı¯ä»¥
    0.08
    ä¹¡åľŁ
    0.08
    از
    0.08
     Bris
    0.08
    Activations Density 0.023%

    No Known Activations