© 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. 3170
    Prev
    Next
    INDEX
    Explanations

    environmental footprint

    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
    çĬ¶æĢģä¸ĭ
    -0.23
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.23
    ORB
    -0.22
     disarm
    -0.22
     conditions
    -0.22
    çī¹çĤ¹æĺ¯
    -0.22
    undef
    -0.21
    ump
    -0.21
    blr
    -0.21
    teenth
    -0.21
    POSITIVE LOGITS
    è¿ĩ大
    0.28
     footprint
    0.27
    å¾Ī大çļĦ
    0.25
    太大
    0.24
     Manit
    0.24
    izzly
    0.23
     mates
    0.23
     Bella
    0.23
    è¶Ĭ大
    0.23
    ä¸įå°ı
    0.22
    Activations Density 0.007%

    No Known Activations