© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10591
    Prev
    Next
    INDEX
    Explanations

    referring to past time

    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
    éĢŁ
    -0.10
    æıIJåīį
    -0.10
     tard
    -0.09
    ìķ¼
    -0.09
    oze
    -0.09
    æĿ¥èĩª
    -0.09
    -offs
    -0.09
    èĥĮåIJİ
    -0.09
    ænd
    -0.09
    åīįéĢĶ
    -0.09
    POSITIVE LOGITS
    ä¸ĢåĪ»
    0.11
    太ä¹ħ
    0.10
    åĩłæŃ¥
    0.10
    建åħļ
    0.10
    åĪ©å¥½
    0.09
    çļĦ缮åħī
    0.09
    æľĽåİ»
    0.09
    çĽĤ
    0.09
    人éĥ½
    0.08
    æīĵçĿĢ
    0.08
    Activations Density 0.039%

    No Known Activations