© 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. 16809
    Prev
    Next
    INDEX
    Explanations

    first followed by a noun

    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
    åī¯
    -0.10
    å¤ļå¹´åīį
    -0.10
    åīį身
    -0.10
    åīįçŀ»
    -0.09
    åīįéĢĶ
    -0.09
    æĹ©å°±
    -0.09
     earlier
    -0.09
    缩åĩı
    -0.09
    oric
    -0.09
    segue
    -0.09
    POSITIVE LOGITS
    èĩªæĿ¥
    0.10
    ä¸Ģæī¹
    0.09
    ë²
    0.09
     immediate
    0.09
    æºī
    0.09
    è¡·
    0.09
    atown
    0.08
    åłij
    0.08
    åĴĮçĿ¦
    0.08
    oku
    0.08
    Activations Density 0.101%

    No Known Activations