© 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. 9
    Prev
    Next
    INDEX
    Explanations

    device and data

    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
    worthy
    -0.22
    ç±¼
    -0.22
     Krist
    -0.21
    /embed
    -0.21
    COME
    -0.21
     Kag
    -0.21
     Antar
    -0.21
    åħ¶å®ŀ
    -0.20
     come
    -0.20
    agement
    -0.20
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.35
    æīĢåľ¨
    0.26
    åľ¨æł¡
    0.25
    ä¿Ŀä¿®
    0.24
    æ¦Ĩ
    0.23
    (so
    0.23
    soles
    0.23
    æľ¬èº«çļĦ
    0.23
    inus
    0.22
    æ·ĩ
    0.22
    Activations Density 0.296%

    No Known Activations