© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 188
    Prev
    Next
    INDEX
    Explanations

    predicting and classifying

    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
    merc
    -0.27
    manage
    -0.27
    èħ°éĥ¨
    -0.26
     neg
    -0.25
     Builders
    -0.24
    lopen
    -0.23
     ine
    -0.23
    leftright
    -0.23
     negoci
    -0.22
     Mate
    -0.22
    POSITIVE LOGITS
    é¢Ħæµĭ
    0.55
     predictions
    0.51
     prediction
    0.49
     predicted
    0.49
     predict
    0.46
    predicted
    0.46
     predicting
    0.46
     predicts
    0.45
     Predict
    0.44
    predict
    0.44
    Activations Density 0.126%

    No Known Activations