© 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. 58083
    Prev
    Next
    INDEX
    Explanations

    pop culture

    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
    åĨ³å¿ĥ
    -0.10
    侥幸
    -0.09
    è¦ģæĬĬ
    -0.09
    裸
    -0.09
     Bj
    -0.09
    olare
    -0.09
    å·¥ä½ľä½ľé£İ
    -0.08
    à¹Ĥà¸Ĭ
    -0.08
    .cent
    -0.08
    поÑĩ
    -0.08
    POSITIVE LOGITS
    符åı·
    0.11
    åķĨæłĩ
    0.10
    åķĨä¸ļåĮĸ
    0.10
    æ¶Īè´¹
    0.10
    æ¶Īè´¹åĵģ
    0.10
    åķĨä¸ļ
    0.10
    æĭĽåķĨ
    0.09
    çĨŁçŁ¥
    0.09
     symbols
    0.09
     consumer
    0.09
    Activations Density 0.124%

    No Known Activations