© 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. 52280
    Prev
    Next
    INDEX
    Explanations

    wondering or questioning

    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
    庶
    -0.12
    婶
    -0.08
    ilateral
    -0.08
     pops
    -0.08
    æľī害
    -0.08
    holding
    -0.08
    éĵĪ
    -0.08
    aily
    -0.08
    æĶ¯çº¿
    -0.08
    åħĦ
    -0.08
    POSITIVE LOGITS
    æŃ¤äºº
    0.10
    严èĤĥ
    0.10
    oldt
    0.10
    ä»Ģä¹Īåij¢
    0.09
    ç»Īæŀģ
    0.09
    éķIJ
    0.09
    mess
    0.08
    è¿ij两年
    0.08
     Ended
    0.08
    çľĭäºĨä¸Ģçľ¼
    0.08
    Activations Density 0.046%

    No Known Activations