© 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. 1839
    Prev
    Next
    INDEX
    Explanations

    state of improvement or betterment

    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
    çĦĵ
    -0.10
    vang
    -0.09
    ä»Ļ
    -0.09
    å±İ
    -0.09
    追究
    -0.08
    vince
    -0.08
    çļĦåľ°ä½į
    -0.08
    á»ı
    -0.08
    Impl
    -0.08
    æĹºçĽĽ
    -0.08
    POSITIVE LOGITS
    æĶ¹åĸĦ
    0.18
    好转
    0.16
     improvement
    0.12
     Improvement
    0.12
    æĶ¹è¿Ľ
    0.12
    ç¼ĵ解
    0.11
     improvements
    0.10
    åı£æ°Ķ
    0.10
    æģª
    0.10
     improves
    0.10
    Activations Density 0.059%

    No Known Activations