© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24163
    Prev
    Next
    INDEX
    Explanations

    past tense actions or states

    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
    Negative Logits
    _hal
    -0.10
    å¥¥åľ°
    -0.10
    æıŃæĻĵ
    -0.09
    梦è§ģ
    -0.09
    踯
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
     اÙĦÙħع
    -0.09
    åģ¿
    -0.09
    ä¸Ģçľĭ
    -0.09
     undisclosed
    -0.09
    POSITIVE LOGITS
     ÑĢанее
    0.13
     previously
    0.12
     earlier
    0.11
    åĽŀæĿ¥
    0.10
    å·²ä¹ħçļĦ
    0.09
    以åīį
    0.09
    åĽŀä¾Ĩ
    0.09
     originally
    0.09
    以æĿ¥
    0.09
    åħĪåīį
    0.08
    Activations Density 0.216%

    No Known Activations