© 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. 8805
    Prev
    Next
    INDEX
    Explanations

    we followed by verbs

    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
    eten
    -0.10
    æķı
    -0.10
     yourselves
    -0.10
    isas
    -0.10
    é¢ĺ主
    -0.09
    æĦŁè§¦
    -0.08
    onio
    -0.08
    лей
    -0.08
    们çļĦ
    -0.08
    èĢĮåĩº
    -0.08
    POSITIVE LOGITS
    åģļçļĦ
    0.13
    ç¯ĩ
    0.08
    éģŃ
    0.08
    éĢĤ度
    0.08
    ä»¥äººä¸ºæľ¬
    0.08
    çĦī
    0.08
     insured
    0.08
    ä¸įå¾Ĺå·²
    0.08
    åľ¨å¹¿å·ŀ
    0.08
    å¦ĤæĦı
    0.08
    Activations Density 0.050%

    No Known Activations