© 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. 1439
    Prev
    Next
    INDEX
    Explanations

    indicates consequence or condition

    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
    æijĦå½±
    -0.25
     Tears
    -0.25
     finally
    -0.24
    icip
    -0.23
     ses
    -0.23
     ges
    -0.23
     Musical
    -0.23
     inaugural
    -0.22
     fis
    -0.22
     Kota
    -0.22
    POSITIVE LOGITS
     therefore
    0.32
    æĹłçĸij
    0.29
    æĹłå½¢
    0.28
    å¦ĤæŀľæĪij们
    0.28
    åĵªå®¶
    0.28
    å¾Īéļ¾
    0.27
    æĺ¯åIJ¦åŃĺåľ¨
    0.26
    æ»ĭçĶŁ
    0.26
    è¿ĻæŶåĢĻ
    0.26
    åĽłæѤ
    0.25
    Activations Density 0.168%

    No Known Activations