© 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. 57166
    Prev
    Next
    INDEX
    Explanations

    plastic polymers and ceramics

    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
    æĬ±çĿĢ
    -0.09
    æĹ¶æ®µ
    -0.09
    åĵģä½į
    -0.08
    åĹª
    -0.08
    髦
    -0.08
    è¾Ľèĭ¦
    -0.08
    çīĪæĿĥå½Ĵ
    -0.08
    çļ¿
    -0.08
    è³ĵ
    -0.08
    æįķæįī
    -0.08
    POSITIVE LOGITS
    éĿŀ常éĢĤåIJĪ
    0.10
    æĿIJæĸĻ
    0.09
    дÑĢ
    0.09
    åĪ¶åĵģ
    0.09
    èµĦ
    0.09
    å¹¿æ³Ľ
    0.09
    çijĿ
    0.09
    imits
    0.09
    æĿIJè´¨
    0.08
    夬
    0.08
    Activations Density 0.445%

    No Known Activations