© 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. 19400
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by months or locations

    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¸Ī
    -0.10
    鬼
    -0.10
    æī©
    -0.10
    дол
    -0.10
    .sb
    -0.09
    ULER
    -0.09
    hk
    -0.09
    é¦ĸåħĪæĺ¯
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    æĬĬå®ĥ
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.10
    ç¢İ
    0.09
    çļĦæķ´ä½ĵ
    0.09
    å¢ŀå¹ħ
    0.08
    åºŃ
    0.08
    åĪĴ
    0.08
    å½ĵæĹ¥
    0.08
    æµģåħ¥
    0.08
    æķ´ä¸ª
    0.08
    ãĥķãĥ«
    0.08
    Activations Density 0.107%

    No Known Activations