© 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. 26234
    Prev
    Next
    INDEX
    Explanations

    sacrifice and ritualistic terms

    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
    ç¿°
    -0.10
    漫çĶ»
    -0.10
     нап
    -0.09
    趺
    -0.08
    å¯ħ
    -0.08
    è°ı
    -0.08
    å¿µä½Ľ
    -0.08
    åįıåķĨ
    -0.08
    å¼Ī
    -0.08
     HAPP
    -0.08
    POSITIVE LOGITS
    ç¥Ń
    0.26
    ç¥Ńç¥Ģ
    0.22
    仪å¼ı
    0.18
    ç¥Ģ
    0.15
    çĮ®
    0.15
     ritual
    0.14
     sacrifice
    0.13
    çį»
    0.13
     sacrifices
    0.13
    åĿĽ
    0.13
    Activations Density 0.022%

    No Known Activations