© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    ice cream or science fiction

    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
    undra
    -0.25
    åİļåİļçļĦ
    -0.23
    INDER
    -0.23
    	IN
    -0.22
     expend
    -0.22
     sails
    -0.21
    UTO
    -0.21
     uçu
    -0.21
    级
    -0.21
    é¾Ĥ
    -0.21
    POSITIVE LOGITS
    å¡ĺ
    0.25
    èĮ¶
    0.25
     tea
    0.25
     thoại
    0.23
    ÈĽ
    0.23
     cum
    0.23
     tet
    0.23
    gay
    0.22
    çıĻ
    0.22
    糯米
    0.22
    Activations Density 0.008%

    No Known Activations