© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    time before

    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
    æĬĬæı¡
    -0.09
    已被
    -0.09
    æĿ¾
    -0.08
    éĩįè¦ģæĦıä¹ī
    -0.08
    .lot
    -0.08
    serter
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    سÙĥ
    -0.08
    æĦį
    -0.08
    ç½ķ
    -0.08
    POSITIVE LOGITS
    æīįä¼ļ
    0.13
    æīįèĥ½
    0.12
     пÑĢежде
    0.11
    æĪijæīį
    0.10
    æīįèĥ½å¤Ł
    0.10
    æīįæľī
    0.10
    积累äºĨ
    0.09
    orious
    0.09
    åİĭåĪ¶
    0.09
    æīįåı¯ä»¥
    0.09
    Activations Density 0.037%

    No Known Activations