© 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. 63592
    Prev
    Next
    INDEX
    Explanations

    later or foreign words for later

    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
    åķĨä¸ļ
    -0.09
    çŁŃæľŁ
    -0.09
    çĨ¨
    -0.09
    åĪĽå§ĭ
    -0.08
     rug
    -0.08
     uden
    -0.08
    rac
    -0.08
    ulg
    -0.08
     removeFrom
    -0.08
    以å¾Ģ
    -0.08
    POSITIVE LOGITS
     later
    0.17
    åIJİéĿ¢
    0.14
    later
    0.14
    Later
    0.14
     Later
    0.13
    ä¸ĭéĿ¢
    0.12
    ä¼ļåľ¨
    0.11
     später
    0.11
    åIJİæĿ¥
    0.10
    åIJİéĿ¢çļĦ
    0.10
    Activations Density 0.031%

    No Known Activations