© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9467
    Prev
    Next
    INDEX
    Explanations

    appropriations and spending

    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
    gers
    -0.10
    é£ı
    -0.10
    çĶŁäº§æĢ»å̼
    -0.10
    åľ°å¸¦
    -0.10
    èΏ
    -0.09
    âģ½
    -0.09
    åħ¥éŨ
    -0.09
    龸çİĭ
    -0.09
    ëģĶ
    -0.09
    éĥ½ä¸įæķ¢
    -0.09
    POSITIVE LOGITS
    åķ¬
    0.10
    OrUpdate
    0.10
    descr
    0.10
    orio
    0.09
    TEE
    0.09
     Teh
    0.09
    aus
    0.09
    ately
    0.08
    duct
    0.08
    auc
    0.08
    Activations Density 0.006%

    No Known Activations