© 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. 19403
    Prev
    Next
    INDEX
    Explanations

    wind energy

    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
    è½¹
    -0.10
    侨
    -0.10
    åĴĮåľ°åĮº
    -0.10
    åĸ¬
    -0.10
    ZH
    -0.09
    ãĤĥ
    -0.09
    iosity
    -0.09
    åĴĮæĬĢæľ¯
    -0.09
    æ¨¡æł·
    -0.09
    ço
    -0.09
    POSITIVE LOGITS
     Hicks
    0.08
    è¯ķçĤ¹
    0.08
    æĺ¥é£İ
    0.08
    оÑĩки
    0.08
    berger
    0.08
    ä¸įåħĭ
    0.08
    è¿Ļ项
    0.08
    _DESCRIPTOR
    0.07
    è´¤
    0.07
    ä¸Ģ项
    0.07
    Activations Density 0.046%

    No Known Activations