© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53028
    Prev
    Next
    INDEX
    Explanations

    chiefs, professors, pastors, assistants

    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
    çļĦåĬĽéĩı
    -0.09
    å²ij
    -0.09
    åı«åģļ
    -0.08
    ivar
    -0.08
    ä»İä¸ļ
    -0.08
    roids
    -0.08
    ä¹ĭåĬĽ
    -0.08
    åĬ¿åĬĽ
    -0.08
    rie
    -0.08
    å¾Īæ·±
    -0.08
    POSITIVE LOGITS
    ä¸Ģäºĭ
    0.12
    è¿Ļäºĭ
    0.10
    åħ¼
    0.10
    åģļ大
    0.10
    ä¸Ģè§Ĵ
    0.10
    æĹ¶è®¸
    0.09
    è¿Ļ对äºİ
    0.09
    第ä¸ĢçĻ¾
    0.09
    æĮīçħ§
    0.09
    大åĵ¥
    0.09
    Activations Density 0.109%

    No Known Activations