© 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. 7244
    Prev
    Next
    INDEX
    Explanations

    let us help

    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
     gentlemen
    -0.10
     пÑĢедÑĥÑģмоÑĤÑĢ
    -0.09
    ä¸Ģçľ¼
    -0.09
    intelligence
    -0.09
    身边çļĦ
    -0.09
     Fool
    -0.08
    ycz
    -0.08
    digest
    -0.08
    é£ŀ
    -0.08
    身边
    -0.08
    POSITIVE LOGITS
    åĢ¾
    0.10
    AKE
    0.09
    ä»ĭåħ¥
    0.09
    æ·ħ
    0.08
    imen
    0.08
    cust
    0.08
    çĶŁäº§çļĦ
    0.08
    çļĦ认è¯Ĩ
    0.08
    utions
    0.08
    éĢ£çºĮ
    0.08
    Activations Density 0.188%

    No Known Activations