© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10679
    Prev
    Next
    INDEX
    Explanations

    phrases starting with numbers or specific words like "with", "there"

    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
    å¸Į
    -0.08
    è±ļ
    -0.08
    å¤ĸèµĦ
    -0.08
    绪
    -0.08
    å¼ĢéĢļ
    -0.08
    对åħ¶è¿Ľè¡Į
    -0.08
    è¯Ł
    -0.08
    对åºĶçļĦ
    -0.08
    åİĨåı²æĤłä¹ħ
    -0.08
    ãĥ¬ãĤ¤
    -0.08
    POSITIVE LOGITS
    æĢ»éĩı
    0.10
    æĢ»æķ°
    0.10
    ä¸Ģåħ±
    0.09
    egal
    0.09
    æĤĸ
    0.09
    çŃIJ
    0.09
    åħ±æľī
    0.09
    ä¸Ģè¾¹
    0.09
    æ¯ı人
    0.09
    HIP
    0.09
    Activations Density 0.110%

    No Known Activations