© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33627
    Prev
    Next
    INDEX
    Explanations

    methods, action, obesity, change, awakening

    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
    ä¸Ķ
    -0.10
    ancel
    -0.09
    ãģĭãģ¤
    -0.08
    ctal
    -0.08
    åħĭæľį
    -0.08
    _SF
    -0.08
    OLA
    -0.08
     оказ
    -0.08
    NESS
    -0.08
    yü
    -0.08
    POSITIVE LOGITS
    å¤įä»ĩ
    0.10
    åģļçļĦäºĭ
    0.10
    æľĢ好æĺ¯
    0.09
    èĿ®
    0.09
    èĪ«
    0.09
    æķŀå¼Ģ
    0.09
    临港
    0.08
    ä¸įè¦ģ太
    0.08
    æľīèī²
    0.08
     Kurd
    0.08
    Activations Density 0.420%

    No Known Activations