© 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. 20265
    Prev
    Next
    INDEX
    Explanations

    geographical distribution

    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
    æŁ¥éªĮ
    -0.08
    ä¸Ģ代
    -0.08
    آخر
    -0.08
    utt
    -0.08
    expo
    -0.08
    .createFrom
    -0.08
    æįIJåĬ©
    -0.07
    乩
    -0.07
    bows
    -0.07
     Serena
    -0.07
    POSITIVE LOGITS
    å°ļ
    0.10
    æµ·å¤ĸå¸Ĥåľº
    0.10
    åĮĹç¾İ
    0.10
    åºŃ
    0.10
    å¸ĤåľºçļĦ
    0.10
    çľ¼ä¸Ń
    0.10
    è¿Ļè¾¹
    0.10
    /original
    0.10
    åľ°åĮºçļĦ
    0.09
    éĥ¨åĪĨåľ°åĮº
    0.09
    Activations Density 0.109%

    No Known Activations