© 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. 33551
    Prev
    Next
    INDEX
    Explanations

    organization titles

    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
    åij¨åĽ´çļĦ
    -0.10
    身边çļĦ
    -0.10
    oui
    -0.09
    æģ¶
    -0.09
    æĪijéĻ¢
    -0.09
    åij¨è¾¹
    -0.09
    ä¸įä»ħä»ħæĺ¯
    -0.09
    åij¨åĽ´
    -0.08
     ald
    -0.08
     INA
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.09
    å¦Ĥä¸ĭ
    0.09
    екÑĤ
    0.09
    æݥ轨
    0.08
    ä¹ĭæĺŁ
    0.08
    ä¹ĭä¸Ģ
    0.08
    ayette
    0.08
    对æİ¥
    0.08
     Aviv
    0.08
     nutrition
    0.08
    Activations Density 0.058%

    No Known Activations