© 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. 12235
    Prev
    Next
    INDEX
    Explanations

    shot fired

    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
    ายà¸Ļ
    -0.10
    æĶĢçĻ»
    -0.10
    æİ¥
    -0.09
    éļ¾å¾Ĺ
    -0.09
    bett
    -0.09
    ç²¾ç»Ĩ
    -0.09
     grub
    -0.09
    æį¨
    -0.09
    佬
    -0.09
    xcd
    -0.08
    POSITIVE LOGITS
    åŃIJå¼¹
    0.11
    æīĵåĵį
    0.11
    åıijå°Ħ
    0.10
     shooting
    0.10
    åĩºåİ»
    0.09
     gunshot
    0.09
     envelope
    0.09
    å°Ħåĩ»
    0.09
    æĮīæŶ
    0.09
    å¦Ĥæŀľä½łæĥ³
    0.09
    Activations Density 0.083%

    No Known Activations