© 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. 50277
    Prev
    Next
    INDEX
    Explanations

    in any way or by no means

    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
    èIJ½
    -0.08
    borg
    -0.08
    ä¸įåŃĺåľ¨
    -0.08
    ä»ħä¾ĽåıĤèĢĥ
    -0.08
     Rei
    -0.08
    æľīçļĦ
    -0.08
    inas
    -0.08
    ãģĦãģ¡
    -0.07
    äºĨä¸ĢäºĽ
    -0.07
    oot
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.10
    çłŃ
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    éªĸ
    0.09
    æĿĤè´¨
    0.09
    ç¾²
    0.09
    éĢĬ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    çIJĨä¼ļ
    0.08
    æĪ¢
    0.08
    Activations Density 0.007%

    No Known Activations