© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35303
    Prev
    Next
    INDEX
    Explanations

    security, bank, insurance, airways

    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
     administrator
    -0.08
    æ½ľ
    -0.08
    igen
    -0.08
    æªIJ
    -0.08
    çĩ§
    -0.08
    æѦåĬŁ
    -0.08
    ä¾Ľæ±Ĥ
    -0.08
    积水
    -0.08
    resh
    -0.08
     "
    -0.08
    POSITIVE LOGITS
    人寿
    0.13
    ä¿ĿéĻ©åħ¬åı¸
    0.11
    æݧèĤ¡éĽĨåĽ¢
    0.11
    宾é¦Ĩ
    0.10
    大åݦ
    0.09
    çĭİ
    0.09
     Airways
    0.09
    大éģĵ
    0.09
    åģļçļĦäºĭ
    0.09
     ÑįÑĤÑĥ
    0.09
    Activations Density 0.248%

    No Known Activations