© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    serve basis

    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
    åħ·ä½ĵçļĦ
    -0.24
    äºĨåįĬ天
    -0.24
    æĸ°çļĦ
    -0.23
    åĨħå¿ĥçļĦ
    -0.23
    ние
    -0.22
    åıĭ们
    -0.21
    amic
    -0.21
    æĪIJçĨŁçļĦ
    -0.20
    æľīä¸Ģ个
    -0.20
    ors
    -0.20
    POSITIVE LOGITS
     perspective
    0.25
    è¿Ļä¸Ģ
    0.24
    пÑĥ
    0.24
    ç«ĭåľº
    0.24
    /apt
    0.24
     format
    0.23
    è¡ĮåĪĹ
    0.23
     manner
    0.23
     Mits
    0.23
    èĢı
    0.23
    Activations Density 0.972%

    No Known Activations