© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    more followed by nouns

    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
    fork
    -0.08
    åıĪä¸Ģ次
    -0.08
    éĢīæĭ
    -0.08
    åı¦ä¸Ģ个
    -0.08
    VIN
    -0.08
    esan
    -0.07
    ç»Ŀ大å¤ļæķ°
    -0.07
    nano
    -0.07
    :Add
    -0.07
    esis
    -0.07
    POSITIVE LOGITS
    ernet
    0.09
    éķ¿éķ¿
    0.09
    类似çļĦ
    0.09
    èķĬ
    0.09
    æĽĿåħī
    0.09
    缸è¿ij
    0.09
    æѤ类
    0.09
    uden
    0.08
    æľĿ
    0.08
    usercontent
    0.08
    Activations Density 0.028%

    No Known Activations