© 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. 63128
    Prev
    Next
    INDEX
    Explanations

    light emission and luminescence

    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
    ä¸įåĪ©
    -0.11
     Mats
    -0.10
    èģĺ
    -0.10
    ä»Ģ
    -0.10
    ä¸ĩäºĭ
    -0.09
    æ´¾éģ£
    -0.09
    è¡Įéķ¿
    -0.09
    æł½
    -0.09
    稳åģ¥
    -0.09
    大å®Ĺ
    -0.09
    POSITIVE LOGITS
    çģ¯
    0.19
    çģ¯çģ«
    0.18
    çģ¯åħī
    0.17
     lights
    0.17
    çĩĪ
    0.16
    çħ§æĺİ
    0.15
    çģ¯åħ·
    0.15
    çĤ¹äº®
    0.15
    çħ§äº®
    0.14
    è·¯çģ¯
    0.13
    Activations Density 0.190%

    No Known Activations