© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3297
    Prev
    Next
    INDEX
    Explanations

    such as high importance

    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
    Negative Logits
    æĽ´å¤ļ
    -0.27
    éĤ£äºĽ
    -0.25
     wherever
    -0.25
    æĽ´å¤ļçļĦ
    -0.25
    è¿Ļéĥ¨åĪĨ
    -0.25
    utor
    -0.24
    æĽ´å¥½
    -0.24
    æĪĸèĢħ
    -0.24
    ä¸ĭä¸Ģ代
    -0.24
    éĤ£ä¸Ģ
    -0.23
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.27
    è¿Ļä¹Īå¤ļ
    0.25
    åĨµä¸Ķ
    0.25
    è¿Ļä¹Īä¹ħ
    0.25
    å¦ĤæѤ
    0.25
    æľīè¿Ļæł·çļĦ
    0.24
     pigeon
    0.23
    è¿Ļä¹Ī大
    0.22
    éģ½
    0.22
    éĹ³
    0.22
    Activations Density 0.037%

    No Known Activations