© 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. 49190
    Prev
    Next
    INDEX
    Explanations

    year

    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
    elsey
    -0.11
    ä¸ī天
    -0.10
    å¤įå·¥
    -0.10
    æģ»
    -0.10
    两天
    -0.10
    atics
    -0.10
    æľĪåĪĿ
    -0.09
    æİĴéĻ¤
    -0.09
    udos
    -0.09
    çİ°æľī
    -0.09
    POSITIVE LOGITS
    è¿Ļä¸Ģå¹´
    0.20
     year
    0.16
    å¹´
    0.15
    .year
    0.15
    year
    0.15
     годÑĥ
    0.14
     année
    0.14
    å¹´éĹ´
    0.14
    (year
    0.14
    å¹´ãģ®
    0.14
    Activations Density 0.141%

    No Known Activations