© 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. 7923
    Prev
    Next
    INDEX
    Explanations

    analyze systems, study parameters, determine if

    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
    åħ±é¸£
    -0.09
     Structural
    -0.09
    å®ŀä¾ĭ
    -0.08
     Struct
    -0.08
    ä¼¼ä¹İ
    -0.08
    çļĦæĹ¶ä»£
    -0.08
    frey
    -0.08
    åģľå·¥
    -0.08
     structural
    -0.08
    acom
    -0.08
    POSITIVE LOGITS
    éĢ¼
    0.11
    å°ĨæĿ¥
    0.10
    ä¸ºçĽ®çļĦ
    0.09
    æĪ¢
    0.09
     bÄĥng
    0.09
    磨
    0.09
    åħ¨å¤©
    0.09
    缩
    0.09
    éĶ»
    0.09
    å©ļ
    0.08
    Activations Density 0.128%

    No Known Activations