© 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. 457
    Prev
    Next
    INDEX
    Explanations

    ingredients and food items

    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
    tÃŃ
    -0.23
     maxHeight
    -0.23
    InSection
    -0.23
    æ¸Į
    -0.22
    æĮĸ
    -0.22
     tug
    -0.22
     neutral
    -0.22
     гÑĢаÑĦ
    -0.22
    åIJĥ饱
    -0.22
     Swan
    -0.22
    POSITIVE LOGITS
    å¥Ĺè£ħ
    0.24
    çĶŁäº§åİĤ家
    0.24
    pac
    0.23
     NRF
    0.23
     PX
    0.23
    æ´Ĵ
    0.22
    主ç¼ĸ
    0.22
    ä»£æĽ¿
    0.22
    FFE
    0.22
    imon
    0.22
    Activations Density 0.002%

    No Known Activations