© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    electoral redistribution, ghost crabs, viewport, SN

    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
    ä¸įèī¯ä¿¡æģ¯
    -0.24
    inté
    -0.21
    è¶ħé¢Ŀ
    -0.21
    ropical
    -0.21
     NotSupportedException
    -0.21
     succ
    -0.21
    eson
    -0.21
    åľ¨è¿Ļç§į
    -0.20
    -liter
    -0.20
    æ°ĹãģĮ
    -0.20
    POSITIVE LOGITS
    æİĸ
    0.25
    åħģ
    0.23
    åĩºåĵģ
    0.23
    é©»
    0.22
    æĹ¢
    0.22
     ÑĨена
    0.22
    å¾ħ
    0.21
    éļı
    0.21
    PPP
    0.21
    çıŃ
    0.21
    Activations Density 0.362%

    No Known Activations