© 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. 100
    Prev
    Next
    INDEX
    Explanations

    loss or lack

    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
    ãģ¥
    -0.22
    æĶ¾å®½
    -0.20
     bey
    -0.20
    ORK
    -0.20
    æŃĩ
    -0.19
    好æ¶Īæģ¯
    -0.19
     FIXME
    -0.19
    åĪ°æĿ¥
    -0.19
    piece
    -0.18
    gebn
    -0.18
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.28
    èħ´
    0.27
     лиÑĪ
    0.23
    è¶³å¤ŁçļĦ
    0.21
    太å¤ļ
    0.21
     essentials
    0.21
     dignity
    0.20
    æĸ¯é¡¿
    0.20
    -of
    0.20
     fq
    0.20
    Activations Density 0.022%

    No Known Activations