© 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. 51628
    Prev
    Next
    INDEX
    Explanations

    setting aside or away

    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
    ÑĥлÑĮ
    -0.09
    istic
    -0.08
    icut
    -0.08
    ìį¨
    -0.08
    æİĮæı¡
    -0.08
    è¹Ĭ
    -0.08
    ë³´ê³ł
    -0.08
    essian
    -0.08
    ipeg
    -0.08
    sure
    -0.08
    POSITIVE LOGITS
    äºĨä»ĸçļĦ
    0.11
    äºĨ大éĩıçļĦ
    0.11
    æĥ
    0.10
    äºĨä¸Ģ份
    0.10
    äºĨä¸ĢäºĽ
    0.10
    祷
    0.10
    äºĨä¸įå°ij
    0.10
    äºĨ许å¤ļ
    0.09
    äºĨå¤ļå°ij
    0.09
    äºĨæĪijçļĦ
    0.09
    Activations Density 0.010%

    No Known Activations