© 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. 56501
    Prev
    Next
    INDEX
    Explanations

    economic indicators

    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
    atre
    -0.11
    åħļåĴĮåĽ½å®¶
    -0.09
    riel
    -0.09
    dock
    -0.09
    lio
    -0.08
    鸰
    -0.08
    åĪ«
    -0.08
    lef
    -0.08
    .REG
    -0.08
    èĢĮåıĪ
    -0.08
    POSITIVE LOGITS
    é¦ĸ个
    0.11
    é¦ĸ次
    0.10
    åĭĭ
    0.10
    éĢ¼è¿ij
    0.10
    ä¸ĢåĪĩéĥ½
    0.10
    æķ´ä½ĵ
    0.09
    ashes
    0.09
    ç¾İåĽ½äºº
    0.09
    ç¨įç¨į
    0.09
    ä¸ĢåĪĩ
    0.09
    Activations Density 0.038%

    No Known Activations