© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37084
    Prev
    Next
    INDEX
    Explanations

    continues

    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
    éĹ¹
    -0.09
    å¯IJ
    -0.09
    èĦ±èIJ½
    -0.08
    趸
    -0.08
     equally
    -0.08
    /help
    -0.08
    æĦıè§ģ
    -0.08
    uite
    -0.08
    æĪIJæŀľ
    -0.08
    _cast
    -0.08
    POSITIVE LOGITS
    æ®Ĭ
    0.11
     Hawkins
    0.09
    ç´ł
    0.08
     ÑĢабоÑĤÑĥ
    0.08
    åIJij举
    0.08
    robat
    0.08
    ä¸įçĶ±
    0.08
    uly
    0.08
    ç¾ģ
    0.08
     Bout
    0.08
    Activations Density 0.037%

    No Known Activations