© 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. 24318
    Prev
    Next
    INDEX
    Explanations

    expressly/hereby granted

    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
    eker
    -0.10
    openh
    -0.10
    ily
    -0.10
    æĺ¯ä¸Ģä½į
    -0.10
    ely
    -0.09
    å·´æĸ¯
    -0.09
    çŃ¾ç½²
    -0.09
    ä¸Ĭæ¼Ķ
    -0.09
    .amazonaws
    -0.09
    arra
    -0.08
    POSITIVE LOGITS
    æijĩ
    0.09
    ä¸Ģå¹ħ
    0.09
    åĢı
    0.09
    æݬ
    0.08
    ä¸ĢåŃĹ
    0.08
    IAN
    0.08
     withdrawal
    0.08
    éŨåı£
    0.08
    忽
    0.08
    essional
    0.08
    Activations Density 0.118%

    No Known Activations