© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    college sports

    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
    ableObject
    -0.27
    åľ¨ç½ij绾
    -0.25
    ovel
    -0.25
     Urg
    -0.24
     Installing
    -0.22
    年产åĢ¼
    -0.22
    apa
    -0.21
     Ludwig
    -0.21
     borough
    -0.21
     Gutenberg
    -0.21
    POSITIVE LOGITS
    èµĽäºĭ
    0.28
    èģĶèµĽ
    0.28
    ç«ŀ
    0.25
    æ¯ĶèµĽ
    0.25
     rivalry
    0.25
     football
    0.24
     baseball
    0.24
    /state
    0.24
     athletics
    0.23
    çī¹åĪ«æĺ¯
    0.23
    Activations Density 0.007%

    No Known Activations