© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 293
    Prev
    Next
    INDEX
    Explanations

    scholarships and fellowships

    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
    ç®±åŃIJ
    -0.24
    大æ£ļ
    -0.24
    alles
    -0.23
     raided
    -0.23
     Romans
    -0.23
     scape
    -0.23
    解æķ£
    -0.23
    ordered
    -0.23
    udded
    -0.23
    çĭĤ欢
    -0.23
    POSITIVE LOGITS
     scholarships
    0.52
     scholarship
    0.48
    å¥ĸåѦéĩij
    0.48
    åIJįé¢Ŀ
    0.45
     Scholarship
    0.40
    å¥ĸåĬ±
    0.39
    åĬ©åѦ
    0.39
    åѦåŃIJ
    0.39
     award
    0.38
    å¥ĸ项
    0.36
    Activations Density 0.032%

    No Known Activations