© 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. 9248
    Prev
    Next
    INDEX
    Explanations

    .com domains and websites

    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
    çģ¾
    -0.10
    ä¸ºæł¸å¿ĥ
    -0.10
    å¼ĭ
    -0.09
    æ·ħ
    -0.09
    rock
    -0.09
    ctxt
    -0.09
    ç¼ĿéļĻ
    -0.08
    ONY
    -0.08
    é»ijçĻ½
    -0.08
    æľ¬æĬ¥
    -0.08
    POSITIVE LOGITS
    .com
    0.17
    èĿ®
    0.10
    ç½ij
    0.10
    ä¸Ĭæľī
    0.10
    ä¸Ĭãģ§
    0.10
    .net
    0.09
    ä¸ĬçļĦ
    0.09
    .COM
    0.09
    æ°´æĻ¶
    0.09
    ahr
    0.09
    Activations Density 0.060%

    No Known Activations