© 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. 387
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
     https
    -0.47
    ç½ij红
    -0.43
    https
    -0.42
     emojis
    -0.42
     selfies
    -0.40
     covid
    -0.39
     selfie
    -0.38
    æĸ°åĨłçĸ«æĥħ
    -0.38
    .emplace
    -0.37
     emoji
    -0.37
    POSITIVE LOGITS
     XHTML
    0.33
    好象
    0.33
     iPod
    0.30
    .xls
    0.29
    =http
    0.28
    .htm
    0.27
    |--
    0.27
     xrange
    0.27
     QtGui
    0.26
     UNIX
    0.26
    Activations Density 2.176%

    No Known Activations