© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    epidemic or pandemic

    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
    ings
    -0.10
    fully
    -0.10
    ward
    -0.10
    å°Ķæĸ¯
    -0.09
    ÙĬب
    -0.09
    enstein
    -0.09
    imately
    -0.08
    åħļç»Ħ
    -0.08
    .percent
    -0.08
    riers
    -0.08
    POSITIVE LOGITS
    ity
    0.10
    -minded
    0.10
    atic
    0.10
    竽
    0.10
    泡泡
    0.09
    omic
    0.09
    izr
    0.09
    åıĭæĥħ
    0.09
    æĢ§çļĦ
    0.09
    ç¼ħçĶ¸
    0.09
    Activations Density 0.023%

    No Known Activations