© 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. 38592
    Prev
    Next
    INDEX
    Explanations

    much beauty, higher output, lesser training

    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
    çļĦ形象
    -0.09
    çݯçIJĥ
    -0.09
    RON
    -0.09
    ASTE
    -0.09
    gabe
    -0.08
    纷纷
    -0.08
    çļĦè¯Ńè¨Ģ
    -0.08
    åıªä¸º
    -0.08
    èIJ¥åķĨ
    -0.08
     Gon
    -0.08
    POSITIVE LOGITS
    è¶Ĭå¤ļ
    0.29
    è¶Ĭé«ĺ
    0.25
    è¶Ĭ好
    0.25
    è¶Ĭæĺ¯
    0.24
    è¶Ĭ大
    0.24
    è¶Ĭ
    0.22
    æĦĪ
    0.21
    å°±è¶Ĭ
    0.17
     cÃłng
    0.17
     closer
    0.13
    Activations Density 0.023%

    No Known Activations