© 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. 93
    Prev
    Next
    INDEX
    Explanations

    serving communities and regions

    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
    è¾ĥéĩı
    -0.26
    æĪĸèĢħåħ¶ä»ĸ
    -0.25
    Successful
    -0.24
    -actions
    -0.24
    _procs
    -0.23
    -Cs
    -0.22
    Formation
    -0.22
    GameOver
    -0.22
    æĪij说
    -0.21
    letal
    -0.21
    POSITIVE LOGITS
     service
    0.32
    ãĤµãĥ¼ãĥĵãĤ¹
    0.31
     communities
    0.29
    æľįåĬ¡
    0.28
    region
    0.28
    éģįåıĬ
    0.28
    人æ°ijæľįåĬ¡
    0.28
    åľ°åĮºçļĦ
    0.27
    人次
    0.27
     needs
    0.27
    Activations Density 0.069%

    No Known Activations