© 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. 34356
    Prev
    Next
    INDEX
    Explanations

    future/later/eventual

    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
    åѦåĪ°
    -0.11
    onta
    -0.10
    éĢŀ
    -0.10
    æĿŀ
    -0.09
    æĪ¾
    -0.09
    æĪ®
    -0.09
    Ñģли
    -0.09
     Roths
    -0.09
    SSF
    -0.09
    enso
    -0.09
    POSITIVE LOGITS
    æĹ¥åIJİ
    0.15
     future
    0.13
    ä»ĬåIJİ
    0.12
    以åIJİ
    0.12
    å°ĨæĿ¥
    0.12
     later
    0.12
     später
    0.11
    Later
    0.11
     eventual
    0.11
     бÑĥд
    0.11
    Activations Density 0.246%

    No Known Activations