© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    former athletes

    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
     nex
    -0.26
    atron
    -0.25
    ensor
    -0.24
    çĽ¯çĿĢ
    -0.23
    nex
    -0.23
    _chip
    -0.22
    Chip
    -0.22
    -term
    -0.22
     Pavel
    -0.22
    émon
    -0.21
    POSITIVE LOGITS
    æªĢ
    0.23
    åķĨæĬ¥
    0.23
    åĴĮ社ä¼ļ
    0.22
    ivan
    0.22
     consisting
    0.22
     Dayton
    0.21
     Cupertino
    0.21
     candles
    0.21
    æŀľæłij
    0.21
    .circular
    0.21
    Activations Density 0.003%

    No Known Activations