© 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. 51935
    Prev
    Next
    INDEX
    Explanations

    artichoke, falafel, tempeh

    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
    оÑĢÑĤ
    -0.10
    ãģĴ
    -0.09
    .mit
    -0.09
    ä¼´ä¾£
    -0.09
    PURE
    -0.09
    ä¸Ģè·¯ä¸Ĭ
    -0.09
    eus
    -0.09
    ⣵
    -0.09
    éĻµ
    -0.09
    注æĦıåĪ°
    -0.09
    POSITIVE LOGITS
    æIJ¬
    0.09
    éĤ£ä¸ĢåĪ»
    0.09
    æĪIJ年人
    0.08
    back
    0.08
    æ·«
    0.08
    backs
    0.08
    ä»£æĽ¿
    0.08
    èļĵ
    0.08
    à¸ļาล
    0.07
     Charl
    0.07
    Activations Density 0.002%

    No Known Activations