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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8588
    Prev
    Next
    INDEX
    Explanations

    improvement and innovation

    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
    æĬµ
    -0.09
    sam
    -0.09
    çIJĩ
    -0.08
    åħŃ大
    -0.08
     налиÑĩие
    -0.08
     Sammy
    -0.08
    SAM
    -0.08
    lest
    -0.08
     standalone
    -0.08
    èĦı
    -0.08
    POSITIVE LOGITS
    æĶ¹è¿Ľ
    0.29
    æĶ¹åĸĦ
    0.29
     improvement
    0.25
     improvements
    0.22
     Improvement
    0.22
     improve
    0.21
     improving
    0.19
    æĶ¹èī¯
    0.18
     improves
    0.18
    è¿ĽæŃ¥
    0.18
    Activations Density 0.109%

    No Known Activations