© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3417
    Prev
    Next
    INDEX
    Explanations

    Facebook, lingvo, opts, model load, Keras, YOLO, copyright

    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
    Negative Logits
    æű
    -0.27
    erals
    -0.26
    FromArray
    -0.25
     trừ
    -0.24
    Activities
    -0.24
     Sabb
    -0.24
    çī©ä»¶
    -0.24
     Americ
    -0.23
    .raise
    -0.23
     Technician
    -0.23
    POSITIVE LOGITS
     pretrained
    0.53
    è®Ńç»ĥ
    0.40
     neural
    0.39
     LSTM
    0.36
     обÑĥÑĩ
    0.35
     tokenizer
    0.35
     variants
    0.34
     trained
    0.34
     Neural
    0.33
     Vanilla
    0.33
    Activations Density 0.195%

    No Known Activations