© 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. 8143
    Prev
    Next
    INDEX
    Explanations

    internal combustion, off-road, vehicles

    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
    robe
    -0.10
    èĻ¹æ¡¥
    -0.09
    olle
    -0.09
    å¿ĥè¡Ģ
    -0.09
    误
    -0.09
    大桥
    -0.09
    æŁ½
    -0.09
    å¦Ĥä½ķåİ»
    -0.09
     ÑĦиÑĢ
    -0.08
    ä½ĵ系建设
    -0.08
    POSITIVE LOGITS
    车è¾Ĩ
    0.10
    æ´Ĵ
    0.10
    èĤ¡
    0.10
    åķĨçĶ¨è½¦
    0.09
    ä¸Ģè¾Ĩ
    0.09
     vehicles
    0.09
    åĻ¨
    0.09
    è¾ĺ
    0.09
    è¾Ĩ
    0.09
    æģ¤
    0.08
    Activations Density 0.163%

    No Known Activations