© 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. 48384
    Prev
    Next
    INDEX
    Explanations

    large datasets and repositories

    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
    å±ŀ
    -0.11
    RIX
    -0.09
    æµĭè¯Ħ
    -0.09
    iteur
    -0.09
    RIES
    -0.09
    æĸĽ
    -0.09
     Shank
    -0.09
    ç½®
    -0.09
    iores
    -0.09
    riad
    -0.09
    POSITIVE LOGITS
    翻身
    0.11
    鲸
    0.10
    äºĨ大éĩıçļĦ
    0.09
    ç»ıéªĮåĢ¼
    0.09
    3
    0.08
     vast
    0.08
    æķĻ导
    0.08
    oy
    0.08
    丰å¯ĮçļĦ
    0.08
    åij¨ä¸ī
    0.08
    Activations Density 0.032%

    No Known Activations