© 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. 7731
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

    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
    åĬŁå¤«
    -0.09
    Ä°L
    -0.08
    ä¸ĢåĽ¢
    -0.08
    åģļåĪ°äºĨ
    -0.08
    antha
    -0.08
    ANTE
    -0.08
    ãĥŃãĥ¼
    -0.08
    åĽĬ
    -0.08
     Vir
    -0.08
    GINE
    -0.08
    POSITIVE LOGITS
    æ·Ģ
    0.12
    æĢİä¹Īçľĭ
    0.10
    èĻİ
    0.10
    Sou
    0.09
    æĮŁ
    0.09
    ä¸Ģ人
    0.09
    elize
    0.09
    åħīèį£
    0.09
     à¹Ĩ
    0.09
    iable
    0.09
    Activations Density 0.004%

    No Known Activations