© 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. 28061
    Prev
    Next
    INDEX
    Explanations

    time related phrases

    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
    åĪĨæł¡
    -0.09
    å½ĵåĪĿ
    -0.08
    åģ¶
    -0.08
    2
    -0.08
    4
    -0.08
    5
    -0.08
    æĿ¥æºIJ
    -0.08
    1
    -0.08
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    è¿Ļåĩłå¤©
    0.12
    cks
    0.11
     ÑģейÑĩаÑģ
    0.11
    å¼ķãģį
    0.10
    æľ¬åij¨
    0.10
    马ä¸Ĭ
    0.10
    rades
    0.09
    æѤåĪ»
    0.09
    ä¸İæѤ
    0.09
    ppv
    0.09
    Activations Density 0.078%

    No Known Activations