© 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. 20933
    Prev
    Next
    INDEX
    Explanations

    still yet can

    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
    otto
    -0.08
    åľĪ
    -0.08
     rdr
    -0.08
    _nth
    -0.08
    æ½®
    -0.08
    æ£į
    -0.08
    prs
    -0.08
    æīĢå¾Ĺ
    -0.08
    Dimensions
    -0.08
    åķ¼
    -0.08
    POSITIVE LOGITS
    åķ¬
    0.10
    çľĭçľĭ
    0.09
     ÑĦоÑĢ
    0.09
    åıijæĮ¥
    0.09
     ÐľÐ¸
    0.09
    å°ļ
    0.09
    angular
    0.09
    лÑİ
    0.09
    å£ķ
    0.09
    _BROWSER
    0.08
    Activations Density 0.034%

    No Known Activations