© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    initials followed by names or 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
    iéndo
    -0.36
    iếc
    -0.31
    ÅŁeh
    -0.31
    tória
    -0.30
    èĶĬ
    -0.30
    yá»ĩn
    -0.29
     nuru
    -0.29
    ä¸Ģç·
    -0.28
    åĮ¼
    -0.28
    èĮĭ
    -0.28
    POSITIVE LOGITS
    çļĦ妻åŃIJ
    0.29
    çļĦåĦ¿åŃIJ
    0.28
    åĮ»çĶŁ
    0.28
     ê·¸ëłĩì§Ģ
    0.27
     Brown
    0.27
     Button
    0.26
    çļĦä»·æł¼
    0.26
    çļĦ人çĶŁ
    0.26
     Young
    0.26
     Re
    0.26
    Activations Density 0.197%

    No Known Activations