© 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. 36037
    Prev
    Next
    INDEX
    Explanations

    I can

    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
    ooting
    -0.10
    å¾Ī好
    -0.09
     пÑĢид
    -0.09
    æĽ´å¥½
    -0.09
    keit
    -0.09
    åĽĽæĸ¹
    -0.09
    สวà¸Ļ
    -0.08
    éļıæĦı
    -0.08
    ç¡®ç«ĭ
    -0.08
    Mine
    -0.08
    POSITIVE LOGITS
    对å¾ħ
    0.10
    å¾Ĺèµ·
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    .Verify
    0.09
    æľºèĥ½
    0.09
    ä½ĵè´¨
    0.09
    对äºİæĪij们
    0.09
    å¹²åĺĽ
    0.09
    æį§
    0.08
    lesen
    0.08
    Activations Density 0.016%

    No Known Activations