© 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. 38664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ±
    -0.10
    __((
    -0.09
    ouses
    -0.09
    Õ©
    -0.09
    æ®Ħ
    -0.09
     Reflex
    -0.09
    EO
    -0.09
    楼ä¸Ĭ
    -0.09
    ä½ıåľ¨
    -0.08
    åıĮè¾¹
    -0.08
    POSITIVE LOGITS
     Rapid
    0.09
    æŀ£
    0.09
    åĪĨè£Ĥ
    0.09
    æŶæĬ¥
    0.09
    å¤įåĪ¶
    0.09
    Copy
    0.08
    rapid
    0.08
    ä¸įæĥľ
    0.08
    æī©å¼ł
    0.08
    memcpy
    0.08
    Activations Density 0.414%

    No Known Activations