© 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. 50999
    Prev
    Next
    INDEX
    Explanations

    postal services and mail delivery

    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
     ÑĦинанÑģ
    -0.10
    åī§åľº
    -0.09
    çļĦçŃĶæ¡Ī
    -0.09
    çļĦåĽŀçŃĶ
    -0.09
    åı¯çĶ¨
    -0.09
    æ¼ıæ°´
    -0.09
    æ·ħ
    -0.09
    ÙĬات
    -0.09
    æī£
    -0.09
    uned
    -0.08
    POSITIVE LOGITS
    åħ¬åĬ¡
    0.11
    çĤ¹å¤ļ
    0.10
    æĬķ
    0.09
     euler
    0.09
    ç½ijçĤ¹
    0.09
    æĴ¸
    0.09
    主æĦı
    0.09
    ogue
    0.09
    çĿ¨
    0.08
    çĶ³è¯ī
    0.08
    Activations Density 0.045%

    No Known Activations