© 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. 10118
    Prev
    Next
    INDEX
    Explanations

    glamorous, fabulous, chic, stunning

    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
    keeper
    -0.10
    oodle
    -0.09
    æ¡£
    -0.09
    olec
    -0.08
    缸åħ³æĸ°éĹ»
    -0.08
    ophil
    -0.08
    åĸĦæĦı
    -0.08
    çĹĩ
    -0.08
    è¿Ļè¯Ŀ
    -0.08
    огÑĢаÑĦ
    -0.08
    POSITIVE LOGITS
    èķ¤
    0.09
     жизни
    0.09
    çļĦåľ°ä½į
    0.09
    ÑijÑĢ
    0.09
    é¬ĵ
    0.09
    缣
    0.09
    æĬ¼
    0.08
    éķ¶
    0.08
    auce
    0.08
    åľ°æ®µ
    0.08
    Activations Density 0.002%

    No Known Activations