© 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. 801
    Prev
    Next
    INDEX
    Explanations

    world after death

    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
    座
    -0.15
    åĿIJ
    -0.11
    èµ·çĤ¹
    -0.09
    ä¸Ģè§Ĵ
    -0.09
     rec
    -0.09
    éĤ´
    -0.09
    åľī
    -0.09
    ios
    -0.08
    aned
    -0.08
     Gran
    -0.08
    POSITIVE LOGITS
    å´¦
    0.09
    æĺıè¿·
    0.09
    æŃ»äº¡
    0.08
    apr
    0.08
    åIJĵå¾Ĺ
    0.08
     death
    0.08
    禾
    0.08
    èij
    0.08
    æī§åĭ¤
    0.08
     Betty
    0.08
    Activations Density 0.018%

    No Known Activations