© 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. 49351
    Prev
    Next
    INDEX
    Explanations

    internet protocols or groups

    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
    äºĮ人
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    lek
    -0.09
    ä¹ĥèĩ³
    -0.08
    ãĥŀãĤ¤
    -0.08
    è¯įæĿ¡
    -0.08
    arn
    -0.08
    亲å±ŀ
    -0.08
    迹
    -0.08
     pcs
    -0.08
    POSITIVE LOGITS
    åĵı
    0.10
    çĭĤ
    0.10
    çIJĨå·¥
    0.09
    оÑĤов
    0.09
    ç£Ķ
    0.09
    erot
    0.09
    éª
    0.09
    æ¸ļ
    0.09
    åģ¶
    0.09
    åľ¨å½ĵåľ°
    0.09
    Activations Density 0.094%

    No Known Activations