© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2338
    Prev
    Next
    INDEX
    Explanations

    as you may know

    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
    Rh
    -0.23
    æĥ³çĿĢ
    -0.23
     covenant
    -0.23
    è¯Ħå®ļ
    -0.22
    认为
    -0.22
    稳
    -0.21
    形象
    -0.21
    _anchor
    -0.21
    æľīæķĪçļĦ
    -0.21
     !"
    -0.20
    POSITIVE LOGITS
     already
    0.30
     recent
    0.30
    -ish
    0.28
    æĪijå·²ç»ı
    0.28
    already
    0.27
     selves
    0.27
     somewhat
    0.26
    è¿Ļ两天
    0.25
     noticed
    0.25
    ä»İåݻ年
    0.24
    Activations Density 0.038%

    No Known Activations