© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2321
    Prev
    Next
    INDEX
    Explanations

    flag flying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     imaginative
    -0.25
    ä¸ĵ注äºİ
    -0.24
    æݢ索
    -0.24
    åĽŀåIJĪ
    -0.24
    èĽĢ
    -0.24
    æ¶ī足
    -0.24
    æī«ä¸Ģæī«
    -0.24
    屿
    -0.23
    æĴ®
    -0.23
     pharm
    -0.23
    POSITIVE LOGITS
    æĤ¬æĮĤ
    0.41
    æĮĤ
    0.31
     mourning
    0.29
    æĮĤåľ¨
    0.29
    åįĩèµ·
    0.28
    éĢ¢
    0.28
    æķ¬
    0.27
     hanging
    0.27
     hangs
    0.27
    æ¯ıéĢ¢
    0.26
    Activations Density 0.011%

    No Known Activations