© 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. 9825
    Prev
    Next
    INDEX
    Explanations

    am [verb]

    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
    Úº
    -0.11
     vá»±c
    -0.10
    ops
    -0.10
    наÑĩ
    -0.10
    л
    -0.09
    è¦ģä¸įçĦ¶
    -0.09
    amate
    -0.09
    wards
    -0.09
    تاÙĨ
    -0.09
    oper
    -0.09
    POSITIVE LOGITS
    sterdam
    0.11
    owed
    0.10
    æĦıæĢĿ
    0.09
    ored
    0.09
    ghan
    0.09
    ÑĤвоÑĢ
    0.09
    ä¹ĭäºĭ
    0.09
    è¿ľæĻ¯
    0.09
    ropriate
    0.08
    /do
    0.08
    Activations Density 0.064%

    No Known Activations