© 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. 17884
    Prev
    Next
    INDEX
    Explanations

    would like

    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
    æīĵèµ¢
    -0.10
    æīĵæŃ»
    -0.09
    认è¯ģ
    -0.09
    åĽ½æĥħ
    -0.09
    æľĢåħ³éĶ®çļĦ
    -0.09
     Kens
    -0.09
    å¨ī
    -0.08
     ÐijÑĥд
    -0.08
    æĪij们ä¼ļ
    -0.08
    éĿŀ常好
    -0.08
    POSITIVE LOGITS
    æĥ³è¦ģ
    0.22
     want
    0.18
    欲
    0.17
    æĥ³åİ»
    0.17
    Want
    0.17
     wants
    0.16
    æĥ³
    0.16
     muá»ijn
    0.16
     wanted
    0.15
    want
    0.15
    Activations Density 0.515%

    No Known Activations