© 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. 10280
    Prev
    Next
    INDEX
    Explanations

    a or an before noun

    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
     mere
    -0.09
    emente
    -0.08
    ãĥĥãĥĦ
    -0.08
    çļĦå°±æĺ¯
    -0.08
    æķĻèĤ²åŁ¹è®Ń
    -0.08
    ãģ®ãģĮ
    -0.08
    å·§åIJĪ
    -0.08
    å¾Ī
    -0.08
     tended
    -0.08
     à¹Ĩ
    -0.08
    POSITIVE LOGITS
    åŃļ
    0.12
    гÑĥ
    0.10
    rok
    0.09
    éĤ£äºĽ
    0.09
     вÑĢа
    0.09
    åŁºæķ°
    0.09
    è¯ļæĦı
    0.09
    ç²¾åįİ
    0.09
    punk
    0.08
     gro
    0.08
    Activations Density 0.260%

    No Known Activations