© 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. 37387
    Prev
    Next
    INDEX
    Explanations

    expressing surprise or amazement

    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
    INAL
    -0.09
    breaking
    -0.09
    blocked
    -0.08
    Ñīий
    -0.08
    werp
    -0.08
    oris
    -0.08
    æ±Ģ
    -0.08
    HEME
    -0.08
    iros
    -0.08
    ities
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.12
     latter
    0.12
    åµĺ
    0.11
    ä¸įå·²
    0.11
    ingly
    0.10
    ãģĹãģı
    0.10
    ðŁı¼
    0.10
    å¼Ģå±Ģ
    0.09
    窿
    0.09
    adm
    0.09
    Activations Density 0.006%

    No Known Activations