© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    survival and persistence

    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
     Arb
    -0.10
    ä¼ģä¸ļæıIJä¾Ľ
    -0.09
    çĹħæ¯ĴæĦŁæŁĵ
    -0.09
    çľĭä»ĸ
    -0.09
    æ¿Ģæĥħ
    -0.08
    èģĭ
    -0.08
    Hits
    -0.08
    _arrow
    -0.08
    沸èħ¾
    -0.08
    Ø®ÙĦ
    -0.08
    POSITIVE LOGITS
    æłĸ
    0.12
    ä¼łæĴŃ
    0.10
    á»Ļ
    0.09
    éĢĤåºĶ
    0.09
    çĶŁåŃĺ
    0.09
    çĶŁåij½åĬĽ
    0.09
    çݯå¢ĥä¸Ń
    0.09
    ä¸ĢæŦ
    0.09
    åŃĺæ´»
    0.09
    opport
    0.09
    Activations Density 0.115%

    No Known Activations