© 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. 5124
    Prev
    Next
    INDEX
    Explanations

    while/at/during/for/when (temporal conjunctions/prepositions)

    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
    èµĸ
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    ProcessEvent
    -0.09
    æĹłæĦı
    -0.08
     nr
    -0.08
    足
    -0.08
     Alan
    -0.08
    åĩŃçĿĢ
    -0.08
    ä¸įæĸŃ
    -0.08
    åĪĿ级
    -0.08
    POSITIVE LOGITS
    åīįæĿ¥
    0.09
    æijĺ
    0.09
     suá»ijt
    0.09
    _nullable
    0.09
     throughout
    0.08
    éĻ¤å¤ĸ
    0.08
    履约
    0.08
    plets
    0.08
    è·³èĪŀ
    0.08
    FileDialog
    0.08
    Activations Density 0.129%

    No Known Activations