© 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. 32223
    Prev
    Next
    INDEX
    Explanations

    protective coatings and finishes

    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
    wal
    -0.11
    æĿŀ
    -0.10
    æĪIJåĬŁçļĦ
    -0.10
    çłĮ
    -0.09
    èħĶ
    -0.09
    sequ
    -0.09
    è§Ħ模æľĢ大
    -0.09
    å¨ģåĬĽ
    -0.09
    æĸ¹åľĨ
    -0.09
    åĩ¡æĺ¯
    -0.09
    POSITIVE LOGITS
    éĩī
    0.09
    amus
    0.08
     espera
    0.08
    æ·³
    0.08
     ↵↵
    0.08
    æĭ±
    0.08
    ifter
    0.08
    æ®ĭ
    0.07
     normalize
    0.07
     Ñĩа
    0.07
    Activations Density 0.083%

    No Known Activations