© 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. 58231
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è§Ħ模æľĢ大
    -0.10
    讼
    -0.10
     Ronald
    -0.09
    æ®Ĭ
    -0.09
    alars
    -0.09
    æīĢæıIJä¾Ľä¹ĭ
    -0.09
    è§Ħ模
    -0.09
    baugh
    -0.09
    ä¹Łèĥ½
    -0.09
    æĿĢäºĨ
    -0.09
    POSITIVE LOGITS
    ules
    0.10
    ä¼IJ
    0.08
    å¥Ĺ
    0.08
    GPC
    0.08
    تÙĩ
    0.08
    é¹³
    0.08
    è¶Ĭ
    0.07
    nop
    0.07
    å¤ĩæ¡Ī
    0.07
    广æĴŃçĶµè§Ĩ
    0.07
    Activations Density 0.000%

    No Known Activations