© 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. 1473
    Prev
    Next
    INDEX
    Explanations

    time until event

    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
    bery
    -0.27
    baum
    -0.27
    岿
    -0.25
    bose
    -0.23
    俱ä¹IJ
    -0.22
    æĸ¹åľĨ
    -0.22
    antis
    -0.22
    ĥģ
    -0.21
    deal
    -0.21
    artment
    -0.21
    POSITIVE LOGITS
    åį³å°ĨåĪ°æĿ¥
    0.44
     imminent
    0.41
    åį³å°Ĩ
    0.40
     remaining
    0.39
     countdown
    0.38
     upcoming
    0.35
     impending
    0.33
     nearing
    0.33
    ä¸įä¹ħ
    0.33
    ä¸įå¤ļ
    0.32
    Activations Density 0.036%

    No Known Activations