© 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. 23654
    Prev
    Next
    INDEX
    Explanations

    Month names, awareness months, holidays

    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
    åı£å²¸
    -0.11
    æ·³
    -0.09
    許
    -0.09
    å
    -0.09
    çĪĨ款
    -0.09
    æģIJæħĮ
    -0.08
    ascript
    -0.08
    ç³Ĭæ¶Ĥ
    -0.08
    lesc
    -0.08
    å£
    -0.08
    POSITIVE LOGITS
     month
    0.11
     week
    0.10
     Month
    0.09
     Week
    0.09
    month
    0.08
    第äºĮ天
    0.08
    aware
    0.08
    ä¸Ģå¹´ä¸Ģ度
    0.08
    çĹħ
    0.08
    Ĭ¶
    0.08
    Activations Density 0.243%

    No Known Activations