© 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. 9172
    Prev
    Next
    INDEX
    Explanations

    Japanese suffixes and names

    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
    èĪĮ头
    -0.12
     Morrow
    -0.09
    иде
    -0.09
    FN
    -0.09
     Micha
    -0.09
    女åŃIJ
    -0.09
    æ¦Ľ
    -0.09
    æ½
    -0.08
    è®®
    -0.08
     saturn
    -0.08
    POSITIVE LOGITS
    ning
    0.10
    èī¯
    0.09
    é£İäºij
    0.09
    Composer
    0.09
    emachine
    0.09
    bang
    0.09
    å¯Ŀ
    0.09
    âĵ
    0.08
    Bang
    0.08
    ç¨Ĺ
    0.08
    Activations Density 0.199%

    No Known Activations