© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1277
    Prev
    Next
    INDEX
    Explanations

    burns and injuries

    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
    æĿĤ
    -0.10
     FAG
    -0.10
    鼾
    -0.10
    à¹Ĥà¸Ľ
    -0.09
    棺
    -0.09
    åħħ
    -0.09
     Jong
    -0.09
    çļĦåĦ¿åŃIJ
    -0.09
    วà¸ĩ
    -0.09
    æĺŃ
    -0.09
    POSITIVE LOGITS
    伤
    0.18
    åıĹ伤
    0.16
     injury
    0.16
     injuries
    0.15
    åĤ·
    0.14
    伤害
    0.14
     Injury
    0.13
    伤çĹħ
    0.12
    æįŁä¼¤
    0.11
    å®īåħ¨äºĭæķħ
    0.11
    Activations Density 0.118%

    No Known Activations