© 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. 20880
    Prev
    Next
    INDEX
    Explanations

    always wanted

    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
    æĮĪ
    -0.12
    å¾Ī满æĦı
    -0.11
    诧
    -0.10
    èįIJ
    -0.10
    ä¸įçĪ±
    -0.10
    åĶ®åIJİ
    -0.09
    éĩĩ纳
    -0.09
    odge
    -0.09
    æł¸å®ļ
    -0.09
    工信éĥ¨
    -0.09
    POSITIVE LOGITS
    åIJijå¾Ģ
    0.21
    梦æĥ³
    0.16
    çIJĨæĥ³çļĦ
    0.15
    æĨ§æĨ¬
    0.15
    çIJĨæĥ³
    0.14
    æ¸´æľĽ
    0.14
    梦
    0.13
    æĥ³è¦ģ
    0.13
    羡æħķ
    0.12
    缮æłĩ
    0.12
    Activations Density 0.109%

    No Known Activations