© 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. 49586
    Prev
    Next
    INDEX
    Explanations

    tech articles

    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
    ouro
    -0.10
    æĦ£
    -0.09
    RS
    -0.09
    家çĶ¨
    -0.09
    åĩĨå¤ĩ
    -0.08
    ä¸į好æĦıæĢĿ
    -0.08
    åĩĨå¤ĩ好
    -0.08
    ç»ĻäºĪäºĨ
    -0.08
    éĢ£
    -0.08
    ön
    -0.08
    POSITIVE LOGITS
    æľīæľºä¼ļ
    0.10
    çĤĻ
    0.10
    æݥ触åĪ°
    0.10
    åħįè´¹
    0.09
    åıĪèĥ½
    0.09
    itech
    0.09
    åıĪæľī
    0.09
    Disposed
    0.09
    çļĦéĤ£ç§į
    0.09
     phạm
    0.09
    Activations Density 0.201%

    No Known Activations