© 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. 38286
    Prev
    Next
    INDEX
    Explanations

    photos pictures visualization

    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
    黩
    -0.08
    å¼¥
    -0.08
    ë§IJ
    -0.08
    çĶŁäº§è½¦éĹ´
    -0.08
    ä¼ı
    -0.08
    Ñħа
    -0.08
    ãģ¨è¨Ģ
    -0.08
    为é¦ĸ
    -0.08
    éªģ
    -0.08
    idd
    -0.08
    POSITIVE LOGITS
    ä»ħä¾ĽåıĤèĢĥ
    0.11
    å¯ĩ
    0.10
    çı¥
    0.09
    èĢĺ
    0.09
    éĢ¼
    0.09
    模çī¹
    0.09
    ãĤ¤ãĥ¡ãĥ¼ãĤ¸
    0.09
    nio
    0.08
    åłĤ
    0.08
    æł¸åĩĨ
    0.08
    Activations Density 0.032%

    No Known Activations