© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40023
    Prev
    Next
    INDEX
    Explanations

    once again

    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
    äºĽè®¸
    -0.12
    äºĨäºĽ
    -0.11
    ä¸ĢçĤ¹åĦ¿
    -0.10
    ç²ķ
    -0.10
    ä»Ģä¹Īåij¢
    -0.10
    年产
    -0.09
    ä¸Ģé»ŀ
    -0.09
    è¿Ļä¹Ī说
    -0.09
    ä¸ĢæĬ¹
    -0.09
    äºĨä¸Ģç³»åĪĹ
    -0.09
    POSITIVE LOGITS
    ely
    0.11
    èĬĻèĵī
    0.10
    .Ui
    0.09
    _attached
    0.09
     Vernon
    0.09
    ÑĢÑı
    0.08
    éĤ¦
    0.08
    á»ĩ
    0.08
    à¹Ī
    0.08
    鼷
    0.08
    Activations Density 0.010%

    No Known Activations