© 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. 31363
    Prev
    Next
    INDEX
    Explanations

    ambient temperature or thermal environment

    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
    alu
    -0.09
    åĬ¨éĿĻ
    -0.08
    éĥ½æľīèĩªå·±
    -0.08
    ç©·
    -0.08
    åĩºæ±Ĺ
    -0.08
    鹿
    -0.08
     Readonly
    -0.08
    æ³Ĭ
    -0.08
    odic
    -0.08
    åºŀ大çļĦ
    -0.08
    POSITIVE LOGITS
    空æ°Ķä¸Ń
    0.11
    æ°Ķ温
    0.10
    空æ°Ķ
    0.09
    åĴĮ社ä¼ļ
    0.09
    éħ¿
    0.09
    éŨçªĹ
    0.09
     VIP
    0.09
    PAL
    0.08
    åľ°æĿ¿
    0.08
    åĴİ
    0.08
    Activations Density 0.066%

    No Known Activations