© 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. 533
    Prev
    Next
    INDEX
    Explanations

    time to do something

    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
    åħīæºIJ
    -0.24
    learner
    -0.23
     fils
    -0.23
     Ñģвоей
    -0.22
    acre
    -0.21
    æĦıè§ģ
    -0.21
    èŀ½
    -0.20
    éĢģç»Ļ
    -0.20
     ability
    -0.20
     Boom
    -0.20
    POSITIVE LOGITS
    /run
    0.23
    ç°ī
    0.22
    aju
    0.21
    =time
    0.21
     pursuits
    0.21
    æļĩ
    0.21
    Everything
    0.21
    /bus
    0.21
    ROY
    0.21
    everything
    0.20
    Activations Density 0.018%

    No Known Activations