© 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. 29880
    Prev
    Next
    INDEX
    Explanations

    legal declarations and confessions

    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
    åij¼åı«
    -0.11
    棹
    -0.09
    Dest
    -0.09
    æ³Ħ
    -0.09
    é¦Ī
    -0.09
    åij¼
    -0.09
    çľ·
    -0.09
    erne
    -0.09
    å¯ĵæĦı
    -0.09
     Dest
    -0.09
    POSITIVE LOGITS
    çŃ¾åŃĹ
    0.13
    äºĨä¸Ģ份
    0.10
    éĤ£ä»½
    0.10
    çŃ¾åIJį
    0.10
    çŃ¾ç½²
    0.10
    æĹ¥è®¯
    0.10
    ä¸Ģ份
    0.09
    æĶ¾å¼ĥ
    0.09
    æįº
    0.09
     affidavit
    0.09
    Activations Density 0.055%

    No Known Activations