© 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. 19029
    Prev
    Next
    INDEX
    Explanations

    Young, Stone, Adams, awards

    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
    å¤ĩ份
    -0.09
    ä¼ĺ
    -0.09
    opic
    -0.09
    æĶ¿åĬ¡
    -0.09
    ãģ¦ãģĦ
    -0.08
    è¾ĸåĮºåĨħ
    -0.08
    ä»İä¸ļ
    -0.08
    çĥŃè®®
    -0.08
    ities
    -0.08
    ï¸ı
    -0.08
    POSITIVE LOGITS
    æĹłæīĢ
    0.09
    两项
    0.09
    cassert
    0.09
    è·ĭ
    0.09
    alic
    0.09
    åį·
    0.08
    ä¸ĢåıĮ
    0.08
    бан
    0.08
    Launching
    0.08
    éĺŁåijĺ
    0.08
    Activations Density 0.002%

    No Known Activations