© 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. 7502
    Prev
    Next
    INDEX
    Explanations

    programming utility conversion

    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
    Checkpoint
    -0.10
    NotificationCenter
    -0.09
    线索
    -0.09
    å½¼
    -0.09
    _checkpoint
    -0.08
    Extent
    -0.08
    é¢Ĺç²Ĵ
    -0.08
    æ¦Ĥæĭ¬
    -0.08
    .setTitle
    -0.08
    ä¸ĬãģĮ
    -0.08
    POSITIVE LOGITS
    æĿĥå¨ģ
    0.10
    æµĭç®Ĺ
    0.09
    ayah
    0.09
     accurate
    0.09
    çļĦåīįæıIJ
    0.09
    culator
    0.09
    åħ¬å¸ĥ
    0.08
     authoritative
    0.08
    ç»Ļåĩº
    0.08
    _conversion
    0.08
    Activations Density 0.306%

    No Known Activations