© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8373
    Prev
    Next
    INDEX
    Explanations

    -themed related

    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
    UPER
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    URED
    -0.09
    ì§ĢëıĦ
    -0.09
     sez
    -0.09
     türl
    -0.09
     çerç
    -0.09
    åĹĵåŃIJ
    -0.09
    éré
    -0.09
     ÑĥÑĩеб
    -0.09
    POSITIVE LOGITS
    -related
    0.12
    缸åħ³çļĦ
    0.10
    æĸ¹éĿ¢
    0.10
     related
    0.10
    åį³å°ĨåĪ°æĿ¥
    0.10
    -themed
    0.10
    æĸ¹éĿ¢çļĦ
    0.10
    related
    0.10
    é¢ĩæľī
    0.09
    è®®é¢ĺ
    0.09
    Activations Density 0.336%

    No Known Activations