© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6953
    Prev
    Next
    INDEX
    Explanations

    named individuals talking

    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
    骤
    -0.09
    æŀ¢çº½
    -0.09
    èµŀåĬ©
    -0.09
    æķ£åıij
    -0.09
    两个人
    -0.09
    é¢ĺ主
    -0.09
    çķħéĶĢ
    -0.08
    ä¸ī人
    -0.08
    çļĵ
    -0.08
     кÑĢÑĥ
    -0.08
    POSITIVE LOGITS
    æĮĩ导ä¸ĭ
    0.12
    麾
    0.10
    åį¦
    0.09
    é¼ĵåĬ±
    0.09
    åĵij
    0.09
    åįģ足
    0.09
    ucz
    0.09
    åĶĨ
    0.09
    带é¢Ĩ
    0.09
    è¿ĺæĥ³
    0.09
    Activations Density 0.025%

    No Known Activations