© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    what followed by question words

    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
    äºŃ
    -0.22
    EMPL
    -0.21
    èĭ«
    -0.21
    ä¹Łå°±æĺ¯
    -0.20
     vers
    -0.20
    èħķ
    -0.20
    山路
    -0.20
     thus
    -0.20
    æŀľ
    -0.19
    PRESS
    -0.19
    POSITIVE LOGITS
    说æĪij
    0.25
    åĢ¼å®Ī
    0.23
    å°±è§īå¾Ĺ
    0.22
    äĮ¹
    0.22
    å¨Ī
    0.22
    ãģ¨ãģ«ãģĭ
    0.22
    ä¸į说
    0.21
    ãģĬäºĴ
    0.21
    manship
    0.21
    çIJ¡
    0.21
    Activations Density 0.018%

    No Known Activations