© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20904
    Prev
    Next
    INDEX
    Explanations

    concepts of sin and guilt

    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
    ç»Ļä»ĸ们
    -0.09
    isd
    -0.09
    æĬ±
    -0.08
    æ¯ħ
    -0.08
    èĪª
    -0.08
    oid
    -0.08
    UTO
    -0.08
    ä¸įç®¡ä½ł
    -0.08
     RID
    -0.08
    å¾Ĵ
    -0.08
    POSITIVE LOGITS
    妯
    0.10
    å°ıä¼Ļä¼´
    0.10
    åħĦå¼Ł
    0.09
    çĶŁæ´»ä¹łæĥ¯
    0.09
    å¿ı
    0.09
    严èĤĥ
    0.09
    诤
    0.09
    积累äºĨ
    0.09
    纪å§Ķ书记
    0.09
     tempt
    0.09
    Activations Density 0.035%

    No Known Activations