© 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. 36936
    Prev
    Next
    INDEX
    Explanations

    trades and professions

    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
    å½ĵäºĭ
    -0.10
    hound
    -0.10
    rams
    -0.09
    éĩįè¦ģæĦıä¹ī
    -0.09
    joy
    -0.09
    é¾
    -0.09
    æĻºåĬĽ
    -0.09
     Swamp
    -0.09
    -anchor
    -0.08
     Sinclair
    -0.08
    POSITIVE LOGITS
    erm
    0.09
    å¥ĹæĪ¿
    0.09
    çļĦåĦ¿åŃIJ
    0.09
    ะ
    0.09
    çļĦ女åĦ¿
    0.09
     SHOP
    0.08
    çļĦæĪ¿åŃIJ
    0.08
    马äºij
    0.08
    å±ij
    0.08
    shop
    0.08
    Activations Density 0.014%

    No Known Activations