© 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. 37465
    Prev
    Next
    INDEX
    Explanations

    gods and goddesses

    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
    é¹ħ
    -0.10
    åįģå¹´
    -0.09
    æłĩå¿ĹçĿĢ
    -0.08
    åĪ»èĭ¦
    -0.08
    软
    -0.08
    ä¸ĢæľŁ
    -0.08
    äºĮæľŁ
    -0.08
    Flo
    -0.08
    4
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    god
    0.13
     gods
    0.13
    主管
    0.13
    ä¸Ĭå¸Ŀ
    0.12
    女ç¥ŀ
    0.12
    ENTA
    0.11
     Gods
    0.10
    çĶ·ç¥ŀ
    0.10
    iams
    0.10
     god
    0.10
    Activations Density 0.050%

    No Known Activations