© 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. 29778
    Prev
    Next
    INDEX
    Explanations

    karma and well-wishing phrases

    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
    æ·¹
    -0.10
     заÑĤ
    -0.10
    еÑģÑĤв
    -0.09
    åĩºåĩ»
    -0.09
    失åĪ©
    -0.09
    æĶ¶ç´§
    -0.09
    .bs
    -0.08
    TES
    -0.08
    Ĺı
    -0.08
    鬣
    -0.08
    POSITIVE LOGITS
    åĬŁå¾·
    0.13
    åĽłæŀľ
    0.12
    ç¼ĺåĪĨ
    0.12
     karma
    0.12
    姻
    0.12
    ç¦ı
    0.11
    å¤Ļ
    0.11
    积
    0.10
    ä»ĬçĶŁ
    0.10
    罪
    0.10
    Activations Density 0.019%

    No Known Activations