© 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. 56114
    Prev
    Next
    INDEX
    Explanations

    classification categories

    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
    è½»è½»åľ°
    -0.10
    ugen
    -0.10
    ä¸įåİ»
    -0.10
    ä¼Ĺ
    -0.09
     trùng
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    çļ±
    -0.09
    åģľçĶµ
    -0.08
    ttl
    -0.08
    FINE
    -0.08
    POSITIVE LOGITS
    å²ĺ
    0.09
    æµĴ
    0.08
    çe
    0.08
    åĽĽä½į
    0.08
     crosses
    0.08
    OrDefault
    0.08
    åŀ«
    0.08
    è¦ģåѦä¼ļ
    0.08
    ctor
    0.08
     Cath
    0.08
    Activations Density 0.089%

    No Known Activations