© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    food preparation and consumption

    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
    ocation
    -0.26
    akis
    -0.24
    åı¤æĢª
    -0.24
     disposition
    -0.24
     osc
    -0.24
     abyss
    -0.24
     philosophical
    -0.23
     Sig
    -0.23
     //~
    -0.23
    sig
    -0.23
    POSITIVE LOGITS
    临æŶ
    0.33
    è¡¥
    0.32
    æıIJåīį
    0.31
    éĩįæĸ°
    0.29
    çħ§æł·
    0.27
    å¾Īæĸ¹ä¾¿
    0.27
     leftover
    0.27
    overn
    0.26
    è¡¥é½IJ
    0.26
    éĩį温
    0.26
    Activations Density 0.008%

    No Known Activations