© 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. 34577
    Prev
    Next
    INDEX
    Explanations

    long time since or ago

    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
    级以ä¸Ĭ
    -0.10
    æĹ¥çĽĬ
    -0.10
    ä¸Ģå®ļ
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    .apple
    -0.09
    utra
    -0.08
    èĭ¥å¹²
    -0.08
    çķ¥å¾®
    -0.08
    3
    -0.08
    大è¡Ĺ
    -0.08
    POSITIVE LOGITS
     ago
    0.14
    积èĵĦ
    0.10
    avy
    0.10
    ago
    0.10
    -fashioned
    0.10
    å¾Īä¹ħ
    0.09
    ä½ı
    0.09
     Ago
    0.09
    /big
    0.08
    ä¼Ĭæĸ¯
    0.08
    Activations Density 0.022%

    No Known Activations