© 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. 63785
    Prev
    Next
    INDEX
    Explanations

    death and bodies

    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
     bail
    -0.09
     Bail
    -0.09
    åİĨåı²æĢ§
    -0.08
    éĢĴ
    -0.08
    å®®
    -0.08
    éĩĮç¨ĭç¢ij
    -0.08
    çĶŁæĹ¥
    -0.08
    ä¸įæĽ¾
    -0.08
    hel
    -0.08
    ause
    -0.08
    POSITIVE LOGITS
     Ven
    0.10
    åħ¨åİ¿
    0.09
    رÙĩ
    0.09
    æķĽ
    0.09
    uren
    0.09
    ely
    0.09
    å¼ĺæī¬
    0.09
    å®ļåĪ¶
    0.08
    itm
    0.08
    stown
    0.08
    Activations Density 0.155%

    No Known Activations