© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36817
    Prev
    Next
    INDEX
    Explanations

    words for necessity or duty

    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
    ä¹Ŀ大
    -0.09
     Irvine
    -0.08
    Mono
    -0.08
    ischer
    -0.08
    æĹ¢åı¯ä»¥
    -0.08
    æł¹æľ¬å°±ä¸į
    -0.08
    ä¸įæħİ
    -0.08
    cle
    -0.08
    Broker
    -0.08
    ä¹į
    -0.08
    POSITIVE LOGITS
    ä¸įæķ¢
    0.14
    æĥĬè®¶
    0.11
    åľ¨æĪijçļĦ
    0.10
    ä¹ĸä¹ĸ
    0.10
    è¸ī
    0.10
    æħij
    0.10
    èĦ¸
    0.09
    гал
    0.09
    对æĪij们
    0.09
    èĥĨ
    0.09
    Activations Density 0.069%

    No Known Activations