© 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. 60599
    Prev
    Next
    INDEX
    Explanations

    extinct, deceased, defunct, passed away

    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
    æľ¬æĿ¥å°±
    -0.10
    è´±
    -0.10
    ä¸įéĶĪ
    -0.09
    åıªè¦ģæľī
    -0.09
    .gnu
    -0.09
    ä¸įçĶĺ
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
     Turnbull
    -0.09
    æ¯Ĵ
    -0.09
    æĽ´æľī
    -0.08
    POSITIVE LOGITS
    éĢĿ
    0.15
    gone
    0.14
     gone
    0.14
     deceased
    0.13
    亡
    0.12
    æ¶Ī失
    0.12
     extinct
    0.12
    æ·ĺæ±°
    0.12
    ä¸įåŃĺåľ¨
    0.12
    åĢĴéĹŃ
    0.12
    Activations Density 0.139%

    No Known Activations