© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6791
    Prev
    Next
    INDEX
    Explanations

    homologous

    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
    ä¸ĢèĦļ
    -0.10
    è®·
    -0.09
    -mouth
    -0.09
    è¥ŀ
    -0.09
    æĢ¡
    -0.09
    工夫
    -0.09
    idos
    -0.09
    asca
    -0.09
    osen
    -0.08
    aby
    -0.08
    POSITIVE LOGITS
    å¸ľ
    0.09
    åħļæĶ¿
    0.09
    æ¦ľ
    0.09
    .Runtime
    0.08
    æĪ´ä¸Ĭ
    0.08
    ä¸įçŁ¥ä¸įè§ī
    0.08
    è¡ĢèĦī
    0.08
    è¶´åľ¨
    0.08
    æľ¬ç½ij
    0.08
    opr
    0.08
    Activations Density 0.172%

    No Known Activations