© 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. 8244
    Prev
    Next
    INDEX
    Explanations

    just + adjective/noun

    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
    ä»¿ä½Ľ
    -0.10
    æĹłæīĢè°ĵ
    -0.09
    ä¼¼ä¹İ
    -0.09
    åı¤ä»Ĭ
    -0.09
    onga
    -0.09
    å¨Ł
    -0.09
    íĪ¬
    -0.08
    æĤłæĤł
    -0.08
    çĮ©
    -0.08
     Vaughan
    -0.08
    POSITIVE LOGITS
     merely
    0.11
    åıªæĺ¯
    0.10
     simply
    0.10
    è¿Ļåıªæĺ¯
    0.10
    æĸ°ä¸Ģè½®
    0.09
     just
    0.09
    .codes
    0.09
     пÑĢоÑģÑĤо
    0.09
    æĺ¯åĽłä¸º
    0.09
    isper
    0.09
    Activations Density 0.247%

    No Known Activations