© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8668
    Prev
    Next
    INDEX
    Explanations

    legislation and public policy

    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
    澳洲
    -0.11
     initialised
    -0.09
    æĤīå°¼
    -0.09
    æĺ¶
    -0.09
     Brisbane
    -0.09
    åij
    -0.09
    åľ°æ¯¯
    -0.08
    ÙĩÙī
    -0.08
    æįĤ
    -0.08
    лÑij
    -0.08
    POSITIVE LOGITS
    avor
    0.10
    æ°ijäºĭ
    0.09
    椽
    0.09
    èĭ±æł¼åħ°
    0.08
    éĺ´éĺ³
    0.08
    èĭ±éķij
    0.08
     Ñ
    0.08
    çĵł
    0.08
     England
    0.08
    Britain
    0.08
    Activations Density 0.654%

    No Known Activations