© 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. 474
    Prev
    Next
    INDEX
    Explanations

    released works or achievements

    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
    ighter
    -0.26
     conform
    -0.25
    éĢģæĿ¥
    -0.23
    å°ıå§IJå§IJ
    -0.23
    æĿĵ
    -0.23
     вмеÑģÑĤ
    -0.23
    ascal
    -0.22
     blindly
    -0.22
    ä¼¼ä¹İ
    -0.22
    æľ¬æĿ¥å°±
    -0.22
    POSITIVE LOGITS
     groundbreaking
    0.29
    ä¸ļçķĮ
    0.28
    èĩ³ä»Ĭ
    0.28
     succès
    0.26
     contrib
    0.26
     accol
    0.25
     acclaim
    0.25
    è´¡çĮ®
    0.25
    åIJİç»Ń
    0.25
     contributions
    0.24
    Activations Density 0.073%

    No Known Activations