© 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. 199
    Prev
    Next
    INDEX
    Explanations

    registered licenses

    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
    PACK
    -0.28
    shal
    -0.26
    uters
    -0.24
    å®ĺåħµ
    -0.24
    mps
    -0.23
    身边çļĦ
    -0.23
    ikit
    -0.23
    Instead
    -0.23
     puzzles
    -0.22
    æ°Ķ温
    -0.22
    POSITIVE LOGITS
    èIJ¥ä¸ļæī§çħ§
    0.43
    æľīæķĪæľŁ
    0.42
    注åĨĮ
    0.40
     registered
    0.40
    å¤ĩæ¡Ī
    0.40
    çīĮçħ§
    0.38
     Registered
    0.38
    æ³ķå®ļ代表
    0.37
    è¯ģ书
    0.36
     licenses
    0.36
    Activations Density 0.035%

    No Known Activations