© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19359
    Prev
    Next
    INDEX
    Explanations

    mail and directory principal objects

    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
    翻身
    -0.10
    .release
    -0.10
    èĽĻ
    -0.09
    缣
    -0.09
    çij¶
    -0.09
    æĮĽ
    -0.09
     Sund
    -0.09
    _ERRORS
    -0.09
     Lamb
    -0.08
    cps
    -0.08
    POSITIVE LOGITS
    umba
    0.09
    çĶŁçIJĨ
    0.09
    Ot
    0.09
    çī¹èī²çļĦ
    0.09
    ted
    0.09
     cbd
    0.08
    å¸Ĥåİ¿
    0.08
    ä¸ĵä¸ļåĮĸ
    0.08
     обÑĢаз
    0.08
     ëĪĦ
    0.08
    Activations Density 0.100%

    No Known Activations