© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8256
    Prev
    Next
    INDEX
    Explanations

    what it's like to

    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
    çľ¼ä¸Ń
    -0.09
    缴éĢļ车
    -0.09
    ä¿¡è´·
    -0.09
    å¹»
    -0.09
    erge
    -0.08
    çĸ¾
    -0.08
    ingu
    -0.08
    ades
    -0.08
    ores
    -0.08
    åıĮçľ¼
    -0.08
    POSITIVE LOGITS
    çĽĤ
    0.10
    ittel
    0.10
    isman
    0.09
     MAL
    0.09
    /how
    0.09
    Ark
    0.09
    æľīæĦıä¹ī
    0.09
    MAL
    0.09
    度è¿ĩ
    0.09
    -Za
    0.09
    Activations Density 0.009%

    No Known Activations