© 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. 12310
    Prev
    Next
    INDEX
    Explanations

    money owed, bills

    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
    å¦Ĥä½ķåİ»
    -0.09
    oard
    -0.08
    ewe
    -0.08
    碾
    -0.08
    寨
    -0.08
    åı°
    -0.08
    趴
    -0.08
    æ·±åħ¥äººå¿ĥ
    -0.08
    模ç³Ĭ
    -0.08
     vag
    -0.08
    POSITIVE LOGITS
     bills
    0.14
     bill
    0.13
    çĶµè´¹
    0.11
    _bill
    0.10
    ä¸¤å¼ł
    0.10
    åĬ¡
    0.10
    éĢĤ度
    0.10
    ä¸Ģå°ģä¿¡
    0.09
    åħ«åį¦
    0.09
    .bill
    0.09
    Activations Density 0.057%

    No Known Activations