© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21065
    Prev
    Next
    INDEX
    Explanations

    idiot | people | uneducated mob

    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
     пÑĢедоÑģÑĤ
    -0.10
    åºij
    -0.09
    ä¾ł
    -0.09
    严åİīæīĵåĩ»
    -0.09
    æľīåIJį
    -0.09
    åł
    -0.09
    åĪ©çī©
    -0.08
    éļĪ
    -0.08
     Famil
    -0.08
    å¯Ĩ
    -0.08
    POSITIVE LOGITS
    笨
    0.14
    ä¸įæĩĤ
    0.13
    èł¢
    0.12
    å¿ĥæĻº
    0.11
    èĤ¤
    0.10
    è®¤çŁ¥
    0.10
    ç«Ł
    0.10
    èģ©
    0.10
    头èĦij
    0.10
    ç´łè´¨
    0.10
    Activations Density 0.072%

    No Known Activations