© 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. 36434
    Prev
    Next
    INDEX
    Explanations

    superlative or comparative degree

    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
    误ä¼ļ
    -0.10
    æ²ī
    -0.09
    sing
    -0.08
    äºĭ项
    -0.08
    especially
    -0.08
    resent
    -0.08
    orno
    -0.08
    ç°¸
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    aland
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.09
    èµŀèªī
    0.09
    æľīäºĽäºº
    0.09
    è¿Ļæīįæĺ¯
    0.09
    åħ¶ä»ĸ人
    0.09
    åħ¶ä»ĸ
    0.09
    ardi
    0.09
    iest
    0.09
    æĪij们认为
    0.09
    媲
    0.09
    Activations Density 0.097%

    No Known Activations