© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63853
    Prev
    Next
    INDEX
    Explanations

    artichoke, arstechnica.com, work function, galactooligosaccharides

    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
    Negative Logits
    å¼±
    -0.10
    çĨŁçŁ¥
    -0.09
    åį¦
    -0.08
    pa
    -0.08
    èµ°åIJij
    -0.08
    æĴ
    -0.08
    æĬĦ
    -0.08
    äººæł¼
    -0.07
    åīįéĢĶ
    -0.07
    åĬŁè¯¾
    -0.07
    POSITIVE LOGITS
    èį¡
    0.09
    ä¸Ĭå®ĺ
    0.09
    hire
    0.09
    åı¶çīĩ
    0.09
    åıĮæīĭ
    0.09
    ç¾
    0.09
    æ¿ij
    0.09
    èļ±
    0.09
    DataURL
    0.09
    è¡ĮæĶ¿åĮº
    0.09
    Activations Density 0.001%

    No Known Activations