© 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. 5886
    Prev
    Next
    INDEX
    Explanations

    be paid or attributed

    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
    大è§Ħ模
    -0.08
    è°ģèĥ½
    -0.08
    ä¹°çļĦ
    -0.08
    饵
    -0.08
    æĹ·
    -0.08
    éĢįéģ¥
    -0.08
    é«ĺ端
    -0.08
    uit
    -0.08
    æī¹éĩı
    -0.08
    å¾Ī容æĺĵ
    -0.08
    POSITIVE LOGITS
    èģĶç³»
    0.09
    éĺ¿å¯Į
    0.09
    ç½ij讯
    0.09
    æģ¤
    0.09
    åĪ°
    0.09
     пÑĢиÑĩ
    0.09
    秣
    0.08
     пен
    0.08
    NJ
    0.08
    /reference
    0.08
    Activations Density 0.001%

    No Known Activations