© 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. 61130
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and documents

    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
    åĪ¤
    -0.08
    gos
    -0.08
    æľĢç¾İçļĦ
    -0.08
    路线
    -0.08
    éĥ½æĺ¯éĿŀ常
    -0.08
     ÅŁu
    -0.08
    rames
    -0.08
    à¹Ģà¸Īà¸Ń
    -0.08
    éĤ£è¾¹
    -0.08
    shelf
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.09
    æŶ任
    0.08
    以åħ¶
    0.08
    åIJį为
    0.08
    ãģĬãĤĬ
    0.08
     "[
    0.08
    å½ĵæŶ
    0.07
    åħ±åIJĮä½ĵ
    0.07
    åīįè¿°
    0.07
    atrix
    0.07
    Activations Density 0.340%

    No Known Activations