© 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. 56369
    Prev
    Next
    INDEX
    Explanations

    capital and funds

    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
    inton
    -0.09
    brands
    -0.09
    è¿Ŀ
    -0.09
    ç¬ij
    -0.09
    åįĩ
    -0.09
    åį°
    -0.09
    ãĤ¤ãĥĻ
    -0.09
    _iface
    -0.09
     medically
    -0.08
    纤
    -0.08
    POSITIVE LOGITS
    æĬķèµĦé¡¹çĽ®
    0.11
    åĭŁéĽĨèµĦéĩij
    0.10
    çĿ¡è§ī
    0.10
    èµĦéĩij
    0.10
    çŃ¹éĽĨ
    0.10
     vá»ijn
    0.10
    æĬķè³ĩ
    0.09
     investments
    0.09
    YPE
    0.09
    å¤ļä½Ļ
    0.09
    Activations Density 0.037%

    No Known Activations