© 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. 2790
    Prev
    Next
    INDEX
    Explanations

    imagination and ingenuity

    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
    ä¹ł
    -0.09
    éľģ
    -0.09
    istani
    -0.08
    mith
    -0.08
    æĸ°æĶ¿
    -0.08
    fic
    -0.08
    éĩįè¦ģåĨħ容
    -0.08
    سÙĥ
    -0.08
    çij¾
    -0.08
    å¼¼
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    åħħ足çļĦ
    0.09
    Separated
    0.09
    ä¸į顾
    0.09
    baum
    0.09
    éŃĦ
    0.09
    åĬ¡å®ŀ
    0.09
    Mounted
    0.09
    AndServe
    0.09
    åĪĨæµģ
    0.08
    Activations Density 0.005%

    No Known Activations