© 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. 51648
    Prev
    Next
    INDEX
    Explanations

    school of

    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¤ļå°ijéĴ±
    -0.10
    .awt
    -0.09
    xcc
    -0.08
    åĨ³æĪĺ
    -0.08
    äd
    -0.08
     Associates
    -0.08
     adel
    -0.08
    个人信æģ¯
    -0.08
    æģ¢å¤į
    -0.08
    /router
    -0.08
    POSITIVE LOGITS
    å¥ī
    0.10
    bsp
    0.10
    ç»Ī身
    0.09
    åĢ¦
    0.09
    ìľ¼
    0.09
    佶
    0.09
    dir
    0.09
    ä¸Ģæī¹
    0.08
    ä¸Ģè´¯
    0.08
    婺
    0.08
    Activations Density 0.091%

    No Known Activations