© 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. 16774
    Prev
    Next
    INDEX
    Explanations

    Henri, Rene, Enriquez

    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
    è·ijäºĨ
    -0.10
    HTTPHeader
    -0.10
    imeter
    -0.10
    æĢª
    -0.10
    æĹ¥çħ§
    -0.10
    rary
    -0.09
    以èī²
    -0.09
     renewal
    -0.09
    äºĨä»ĸçļĦ
    -0.09
    åĨįå¤ļ
    -0.09
    POSITIVE LOGITS
    ively
    0.10
    atra
    0.10
    urations
    0.10
    ogn
    0.09
    ette
    0.08
    ìłĪ
    0.08
    нÑĭ
    0.08
    ights
    0.08
    大åħ¨
    0.08
    ï¸ı
    0.08
    Activations Density 0.002%

    No Known Activations