© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    setting of time periods

    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
    æĪIJåijĺåįķä½į
    -0.25
    æĤ¨çļĦ
    -0.24
    åħ¥å¸Ĥ
    -0.23
    GREE
    -0.23
    æµĭç®Ĺ
    -0.23
    associated
    -0.23
    élection
    -0.23
    æ½ľèĥ½
    -0.23
    ç«ŀä»·
    -0.22
    others
    -0.22
    POSITIVE LOGITS
     fictional
    0.35
    çݯå¢ĥ
    0.29
     setting
    0.28
     Setting
    0.27
    å°ģéĹŃ
    0.27
    åİŁåŀĭ
    0.27
    setting
    0.26
    cal
    0.26
     isolation
    0.26
     genre
    0.26
    Activations Density 0.060%

    No Known Activations