© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    Project Summary

    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
    äºĭ件
    -0.27
    太快
    -0.26
    ä¹ĭåIJİ
    -0.25
    åİ»ä¸ĸ
    -0.25
    IME
    -0.25
    hang
    -0.24
    éĻ¤éĿŀ
    -0.24
     http
    -0.24
     posters
    -0.24
     event
    -0.23
    POSITIVE LOGITS
     ingredients
    0.33
    ç²¾éĢī
    0.32
     antioxidants
    0.32
    æĬĹæ°§åĮĸ
    0.32
     synerg
    0.30
    éħįæĸ¹
    0.30
    æĪIJåĪĨ
    0.30
     carefully
    0.29
    æĪIJ份
    0.29
    åIJ«éĩı
    0.29
    Activations Density 0.039%

    No Known Activations