© 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. 48094
    Prev
    Next
    INDEX
    Explanations

    heat transfer and energy dissipation

    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
    ÑĢез
    -0.10
    æĬĸ
    -0.09
    -bin
    -0.09
    è§ģéĿ¢
    -0.09
    æłĩ注
    -0.09
    èĬĬ
    -0.09
    æ±ľ
    -0.09
    åľ°ä¸ĭ室
    -0.09
    .getWriter
    -0.08
    å¥ĭ
    -0.08
    POSITIVE LOGITS
    ä¼łéĢĴ
    0.12
    çĥŃéĩı
    0.11
    ä¼łå¯¼
    0.11
    é³ŀ
    0.09
    æķ£çĥŃ
    0.09
    社ä¼ļåĮĸ
    0.09
     heat
    0.09
     exchanges
    0.09
    itta
    0.08
     named
    0.08
    Activations Density 0.096%

    No Known Activations