© 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. 10905
    Prev
    Next
    INDEX
    Explanations

    beef and cattle

    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
    主ä¹ī
    -0.10
    们
    -0.09
    ipp
    -0.09
    maal
    -0.09
    éĶ·
    -0.09
    æ¿ł
    -0.09
    åĽ´
    -0.09
    线ä¸ĭ
    -0.09
    åģ¥åħ¨
    -0.09
    å¾·å°Ķ
    -0.09
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.08
    å¤ļæł·åĮĸ
    0.08
    иков
    0.08
     Woodward
    0.08
    orris
    0.08
    éĻIJ
    0.08
     Nä
    0.08
    åĶ
    0.08
    pter
    0.08
    æĺ¯ä»İ
    0.08
    Activations Density 0.006%

    No Known Activations