© 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. 40178
    Prev
    Next
    INDEX
    Explanations

    bolus doses and flux

    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
    é³ŀ
    -0.09
    顺åĬ¿
    -0.09
    éĢ¢
    -0.08
    ÑĢож
    -0.08
    minster
    -0.08
    å¤§åĽ½
    -0.08
     retro
    -0.08
    adic
    -0.08
    åĽŀ头
    -0.08
    èĺ§
    -0.08
    POSITIVE LOGITS
    éĶIJ
    0.10
    æĭħ
    0.09
    æĮĩçĿĢ
    0.09
    å°¤
    0.09
    charger
    0.09
    缴åįĩ
    0.08
    phant
    0.08
    æİĴæĸ¥
    0.08
    èĵĦ
    0.08
    éĤ¦
    0.08
    Activations Density 0.044%

    No Known Activations