© 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. 9996
    Prev
    Next
    INDEX
    Explanations

    international students

    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
    _trampoline
    -0.09
    åĽłåľ°åĪ¶å®ľ
    -0.09
    åİ»è¿ĩ
    -0.09
    æĩĤå¾Ĺ
    -0.09
    æ´»
    -0.09
    ç¦Ģ
    -0.08
    åķĨåŁİ
    -0.08
     cuffs
    -0.08
    amate
    -0.08
    å©
    -0.08
    POSITIVE LOGITS
    æĹ°
    0.10
    Enum
    0.09
    ãģ¤ãĤĤãĤĬ
    0.09
    èIJ¥
    0.09
    å¾Ĵ
    0.09
    åħ¨æĹ¥åĪ¶
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.08
    æŀļ
    0.08
    æĹłè®ºå¦Ĥä½ķ
    0.08
    enum
    0.08
    Activations Density 0.082%

    No Known Activations