© 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. 2154
    Prev
    Next
    INDEX
    Explanations

    human/Homo sapiens

    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
     nominations
    -0.25
    ifle
    -0.25
    è°ĥåīĤ
    -0.25
    ulen
    -0.24
    ç½ijçĤ¹
    -0.24
     refund
    -0.23
     vezes
    -0.23
    needle
    -0.23
    åıįåĵį
    -0.23
     whitelist
    -0.22
    POSITIVE LOGITS
    çĶŁçī©åѦ
    0.38
    æĸĩæĺİ
    0.37
     Homo
    0.37
     humans
    0.34
    -human
    0.33
     civilization
    0.32
     human
    0.31
    人类
    0.31
     biological
    0.31
     anthrop
    0.31
    Activations Density 0.038%

    No Known Activations