© 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. 8949
    Prev
    Next
    INDEX
    Explanations

    S/Sa followed by common suffixes

    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
    ä¸Ģ举
    -0.09
    å½¼æѤ
    -0.08
    æ´Ĵ
    -0.08
     surg
    -0.08
    ä¹ĭå¿ĥ
    -0.08
    缸äºĴ
    -0.08
    /latest
    -0.08
    ç¿Ł
    -0.08
    çĶŁçĶŁ
    -0.08
    Weekly
    -0.07
    POSITIVE LOGITS
    鸳
    0.10
    è°ĥ
    0.09
     Hutchinson
    0.09
    èĺ¸
    0.09
    oord
    0.09
    athi
    0.09
    让她
    0.09
    è¿Ļæĺ¯ä¸Ģç§į
    0.09
    è¦ģä¹Ī
    0.09
     intelligent
    0.08
    Activations Density 0.066%

    No Known Activations