© 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. 50641
    Prev
    Next
    INDEX
    Explanations

    events and dates

    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
    ä¸įå°ı
    -0.09
    å¹´éĻIJ
    -0.09
    éĶŁ
    -0.08
    å¸ĪèĮĥ
    -0.08
    è´¿èµĤ
    -0.08
    鲫
    -0.08
    æѤç§į
    -0.08
    éĹ¯
    -0.08
    ment
    -0.08
    urch
    -0.08
    POSITIVE LOGITS
    ãģĿãĤĮãģ«
    0.10
    irs
    0.09
    ä¸ĸçķĮ级
    0.09
    veau
    0.09
    åħ¨å¹´
    0.09
    åĽ½å®¶æĪĺçķ¥
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    å¤ĸ交
    0.08
    éĩį大
    0.08
    opot
    0.08
    Activations Density 0.004%

    No Known Activations