© 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. 64103
    Prev
    Next
    INDEX
    Explanations

    feel free to

    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
    Negative Logits
    æģIJæĢķ
    -0.11
    çĿĢåĬĽæīĵéĢł
    -0.10
    èĥ½å¤Łè®©
    -0.10
    ä¸įå¿ĺåĪĿå¿ĥ
    -0.09
    çĿ¡è§ī
    -0.09
    åı¯ä»¥æĽ´å¥½
    -0.09
    åĬ²
    -0.09
    åĭģ
    -0.09
    åĺ»åĺ»
    -0.09
    鸱
    -0.09
    POSITIVE LOGITS
    èģĶæĥ³
    0.09
    åıĤ
    0.08
    çķħ
    0.08
    æ·»
    0.08
    èıĬ
    0.08
    ãģ³
    0.08
    VPN
    0.08
    å®£ä¼łæķĻèĤ²
    0.08
    ä»ĸä¹Ł
    0.08
    essler
    0.08
    Activations Density 0.006%

    No Known Activations