© 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. 1897
    Prev
    Next
    INDEX
    Explanations

    days of the week titles

    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
     Resume
    -0.27
    龸çİĭ
    -0.26
    .pat
    -0.24
     summar
    -0.24
     resumes
    -0.24
     REPORT
    -0.23
    çī¹æ´¾åijĺ
    -0.23
     unread
    -0.23
    .resume
    -0.22
     resumed
    -0.22
    POSITIVE LOGITS
    åıłåĬł
    0.24
    patches
    0.23
     ros
    0.23
    iram
    0.23
    framework
    0.23
    ROI
    0.22
    ä½IJ
    0.22
    legates
    0.22
    rv
    0.22
    ä½ı
    0.22
    Activations Density 0.003%

    No Known Activations