© 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. 47937
    Prev
    Next
    INDEX
    Explanations

    what is it

    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
    ä¸Ńæľī
    -0.10
    riad
    -0.09
    shaw
    -0.09
    èĩ³æĸ¼
    -0.09
    çijļ
    -0.09
    ICA
    -0.09
    æĿ³
    -0.08
    æĢ¨
    -0.08
    毫æĹłçĸij
    -0.08
    atak
    -0.08
    POSITIVE LOGITS
     they
    0.10
     Chu
    0.09
    chu
    0.08
    çŁ¿ä¸ļ
    0.08
    gro
    0.08
     that
    0.08
    解æĶ¾
    0.08
    åħ®
    0.07
     we
    0.07
     n
    0.07
    Activations Density 0.020%

    No Known Activations