© 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. 33383
    Prev
    Next
    INDEX
    Explanations

    duration or past existence

    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
    å°±æĺ¯åľ¨
    -0.09
    åİ»æī¾
    -0.09
    åīįæĸ¹
    -0.09
    å°±æĺ¯åĽłä¸º
    -0.09
    åłĨ积
    -0.09
    éĺĸ
    -0.09
    çİ°åľ¨çļĦ
    -0.08
    ë°©
    -0.08
     TimeUnit
    -0.08
    ä¹Łä¸įæĥ³
    -0.08
    POSITIVE LOGITS
    æĪijä¸Ģ缴
    0.10
    ä¸Ģ缴æĺ¯
    0.09
    æľĪ以æĿ¥
    0.09
    æĿ°
    0.09
    以æĿ¥
    0.08
    å¤ļå¹´æĿ¥
    0.08
    å¤ļå¹´
    0.08
    丰满
    0.08
    åįģå¤ļå¹´
    0.08
    议论
    0.08
    Activations Density 0.127%

    No Known Activations