© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36518
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing

    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
    å¯Ł
    -0.10
    åŨ
    -0.09
    çĥĺ
    -0.09
    å¸ĤåľºåĮĸ
    -0.09
    åĿı
    -0.08
    itta
    -0.08
    èĮģ
    -0.08
    èİī
    -0.08
    Æ°á»Łng
    -0.08
    bras
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.17
    æĢ§å¼º
    0.16
    å¾Ĺå¾Ī
    0.12
     nature
    0.12
    itous
    0.11
    æĢ§è´¨
    0.11
    æĢ§åĴĮ
    0.11
    ly
    0.11
     ÙĦÙĦغاÙĬØ©
    0.11
    åįģ足
    0.11
    Activations Density 0.131%

    No Known Activations