© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 492
    Prev
    Next
    INDEX
    Explanations

    word suffixes

    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
    è¹¾
    -0.24
    æĿijåŃIJ
    -0.24
    Outlet
    -0.24
    starter
    -0.24
    ·»
    -0.23
     final
    -0.23
    å«ī
    -0.22
    termination
    -0.22
    final
    -0.22
    Final
    -0.22
    POSITIVE LOGITS
     Mason
    0.26
     petroleum
    0.25
    arna
    0.25
    ä¸ŃåĽ½çļĦ
    0.24
    asonry
    0.24
    ould
    0.24
     Mars
    0.24
    马
    0.24
     human
    0.24
     versus
    0.23
    Activations Density 0.860%

    No Known Activations