© 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. 36500
    Prev
    Next
    INDEX
    Explanations

    past participles followed by articles/prepositions

    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
    ละ
    -0.10
    NESS
    -0.09
    ãģĿãģĵ
    -0.09
    ibel
    -0.09
     Cry
    -0.09
    amus
    -0.09
    æīįæľī
    -0.08
    ãģªãģĬ
    -0.08
    iosity
    -0.08
    ROSS
    -0.08
    POSITIVE LOGITS
    ä¸įå°ı
    0.09
     not
    0.09
    åģļä»Ģä¹Ī
    0.09
    åģİ
    0.09
    å¯Ĥå¯ŀ
    0.09
    å°±æĺ¯è¿Ļæł·
    0.09
    æ±ĩ
    0.09
    ctica
    0.09
    éĿŀ常å¤ļ
    0.09
    å¾Īå¤ļ
    0.09
    Activations Density 0.624%

    No Known Activations