© 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. 49766
    Prev
    Next
    INDEX
    Explanations

    written content descriptions

    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
    oyal
    -0.10
    orders
    -0.10
    wald
    -0.09
    订åįķ
    -0.09
     Tamb
    -0.09
    åıĪ好
    -0.09
    æł¹æºIJ
    -0.09
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    asta
    -0.08
    -orders
    -0.08
    POSITIVE LOGITS
    æŃ£æĸĩ
    0.12
    æĸĩåŃĹ
    0.12
     paragraphs
    0.11
    çļĦæĸĩåŃĹ
    0.10
    çīĮ
    0.10
    æĸĩæ¡Ī
    0.10
    æĶ¹éĿ©åĪĽæĸ°
    0.10
    å°ıåŃIJ
    0.09
     text
    0.09
    åı¥è¯Ŀ
    0.09
    Activations Density 0.094%

    No Known Activations