© 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. 1782
    Prev
    Next
    INDEX
    Explanations

    news and magazine publications

    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
    ooth
    -0.27
    åĮħ
    -0.24
    çĶ·çĶŁ
    -0.24
    ccd
    -0.23
    enda
    -0.23
    utor
    -0.23
    лан
    -0.23
    åľ¨æ¸¸æĪıä¸Ń
    -0.22
     ÑģпоÑģоб
    -0.22
    èĥ½æĬĬ
    -0.21
    POSITIVE LOGITS
     magazine
    0.52
    æĿĤå¿Ĺ
    0.49
     Magazine
    0.46
    æĿĤå¿Ĺ社
    0.42
     magazines
    0.40
    ä¸ĵ访
    0.34
    åij¨åĪĬ
    0.33
     news
    0.33
    news
    0.33
    æľŁåĪĬ
    0.32
    Activations Density 0.071%

    No Known Activations