© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1209
    Prev
    Next
    INDEX
    Explanations

    archives: category or date

    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
    trade
    -0.23
    stances
    -0.23
    æĽ´åĬł
    -0.23
    ç©¿ä¸Ĭ
    -0.23
    arshal
    -0.23
    èĢĮæĺ¯
    -0.23
    urban
    -0.22
     trade
    -0.21
    Interop
    -0.21
    æħĮ
    -0.21
    POSITIVE LOGITS
    MO
    0.24
    æĢ»æĶ¶åħ¥
    0.22
     kap
    0.22
     Slug
    0.22
     slug
    0.22
     Birthday
    0.21
    æĺ¯ä»Ģä¹Īåij¢
    0.21
     ÐľÐ¾
    0.21
     Rey
    0.20
    YM
    0.20
    Activations Density 0.017%

    No Known Activations