© 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. 36411
    Prev
    Next
    INDEX
    Explanations

    online presence and digital world

    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
    _GC
    -0.09
    åIJ¬è§ģ
    -0.09
     Greenland
    -0.09
    æĻº
    -0.09
    æĺ¼
    -0.09
    bang
    -0.09
    å½ĵåľº
    -0.09
    è¿IJéĢģ
    -0.09
    éĩĩ访
    -0.09
    æĻļé¥Ń
    -0.08
    POSITIVE LOGITS
    åľ¨ç½ij绾ä¸Ĭ
    0.15
     online
    0.14
    åľ¨çº¿
    0.13
    线ä¸Ĭ
    0.13
    åľ¨ç½ij绾
    0.12
    online
    0.11
    åľ¨ç½ijä¸Ĭ
    0.11
     Online
    0.11
    线ä¸Ĭ线ä¸ĭ
    0.11
    ãĤªãĥ³ãĥ©ãĤ¤ãĥ³
    0.11
    Activations Density 0.094%

    No Known Activations