© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3344
    Prev
    Next
    INDEX
    Explanations

    shooting tragedies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å¾Ģè¿Ķ
    -0.26
    è°ª
    -0.24
    folio
    -0.24
     migrated
    -0.24
     migrating
    -0.23
    è¿ģ移
    -0.23
    éĻ·éĺ±
    -0.23
     True
    -0.23
    еле
    -0.23
    对åħ¶çľŁå®ŀ
    -0.23
    POSITIVE LOGITS
    åıĪä¸Ģ次
    0.30
    æĤ²åī§
    0.29
     tragedy
    0.29
    äºĭ件
    0.28
    åĨįä¸Ģ次
    0.27
     tragedies
    0.27
     violence
    0.27
    utter
    0.26
    伤亡
    0.26
    æĤ²
    0.26
    Activations Density 0.032%

    No Known Activations