© 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. 36769
    Prev
    Next
    INDEX
    Explanations

    French place names or suffixes

    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
    otch
    -0.10
     влад
    -0.10
    tré
    -0.09
    eut
    -0.09
    fst
    -0.09
    æĬķå½±
    -0.09
    _sensitive
    -0.09
    ÈĽi
    -0.08
    _CRC
    -0.08
    rawn
    -0.08
    POSITIVE LOGITS
     cot
    0.08
    åĪĽæĸ°åıijå±ķ
    0.08
     et
    0.08
    åįİ举
    0.08
    son
    0.08
    éªļ
    0.08
    aver
    0.07
     de
    0.07
    ä¹Łå°±
    0.07
    avis
    0.07
    Activations Density 0.196%

    No Known Activations