© 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. 214
    Prev
    Next
    INDEX
    Explanations

    service contexts

    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
    öz
    -0.24
    inem
    -0.24
    alez
    -0.24
    é¾Ļæ¹ĸ
    -0.23
    irk
    -0.23
    éķľå¤´
    -0.21
    åĪ°ä½į
    -0.21
    alement
    -0.21
    aled
    -0.21
    éĺŁä¼į
    -0.21
    POSITIVE LOGITS
    æıIJä¾ĽåķĨ
    0.28
    åŀ£
    0.24
    çĪ·
    0.24
     tier
    0.22
    usage
    0.22
    landers
    0.22
    è¥ŀ
    0.22
    ÑĦон
    0.21
    åIJį为
    0.21
    æĹ¥æĬ¥ç¤¾
    0.21
    Activations Density 0.032%

    No Known Activations