© 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. 1762
    Prev
    Next
    INDEX
    Explanations

    adulterous or derogatory terms

    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
     susp
    -0.09
    èĢģ人家
    -0.09
    æĹĮ
    -0.09
     Needle
    -0.09
    uite
    -0.09
    éĽªèĬ±
    -0.08
    çIJ®
    -0.08
    两项
    -0.08
    çĤ¹è¯Ħ
    -0.08
    æĤ¬
    -0.08
    POSITIVE LOGITS
    èħIJ
    0.10
    çĭĹ
    0.10
    .Metadata
    0.10
    ãģ¨åħ±
    0.09
    èĪ¬çļĦ
    0.09
    ä¸ĢèĪ¬çļĦ
    0.09
    æ±
    0.09
    laps
    0.09
    å©Ĩ
    0.09
    庸
    0.09
    Activations Density 0.059%

    No Known Activations