© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20173
    Prev
    Next
    INDEX
    Explanations

    law firm names

    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
    æĬ¥ä¸ļ
    -0.09
    ç½ijåıĭè¯Ħ论
    -0.09
     parl
    -0.09
    åĥĸ
    -0.09
    otec
    -0.09
    acco
    -0.09
    anged
    -0.09
    åī¯å¸Ĥéķ¿
    -0.09
    客æľį
    -0.08
    ä¿®åħ»
    -0.08
    POSITIVE LOGITS
    人为
    0.10
     LLP
    0.10
    ç¨ĢåľŁ
    0.09
    ä¸Ĭè°ĥ
    0.09
    åŀĤ
    0.09
     once
    0.08
    å¾Ħ
    0.08
    严谨
    0.08
    ç»´æĿĥ
    0.08
     ngá»Ļ
    0.08
    Activations Density 0.071%

    No Known Activations