© 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. 10213
    Prev
    Next
    INDEX
    Explanations

    just, simply, merely

    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
    è¿ĻéĩĮæľī
    -0.10
    èıŁ
    -0.09
    è¿Ļä¸įæĺ¯
    -0.09
    麾
    -0.09
    å¥Ĺ
    -0.09
     annex
    -0.08
     spect
    -0.08
    eree
    -0.08
    æĪ¾
    -0.08
    iage
    -0.08
    POSITIVE LOGITS
    åıªæĺ¯
    0.29
    ä»ħä»ħæĺ¯
    0.27
    åıªæĺ¯ä¸Ģ个
    0.23
     merely
    0.23
    åıªä¸įè¿ĩæĺ¯
    0.23
     just
    0.22
    ä»ħ为
    0.22
     simply
    0.22
    æĪijåıªæĺ¯
    0.22
     пÑĢоÑģÑĤо
    0.21
    Activations Density 0.234%

    No Known Activations