© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    research and basic science

    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
    Lists
    -0.09
    çĽĺæ´»
    -0.09
    éĺ¶å±Ĥ
    -0.09
    ABS
    -0.08
    涨价
    -0.08
    .struct
    -0.08
    æĪijä»¬çŁ¥éģĵ
    -0.08
    alone
    -0.08
    .osgi
    -0.08
    eton
    -0.08
    POSITIVE LOGITS
     research
    0.29
    ç§ijçłĶ
    0.26
    çłĶ究
    0.25
    research
    0.23
    ç§ijåѦçłĶ究
    0.22
     Research
    0.22
    Research
    0.21
    çłĶ究人åijĺ
    0.20
     researching
    0.20
     researched
    0.19
    Activations Density 0.190%

    No Known Activations