© 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. 24
    Prev
    Next
    INDEX
    Explanations

    getting ready and preparing

    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
    awk
    -0.25
     Stick
    -0.23
    æ´»å¾Ĺ
    -0.23
     repro
    -0.22
    ĪæĿĥ
    -0.22
    æľīä¸Ģ次
    -0.22
    isa
    -0.22
    washer
    -0.22
    iband
    -0.21
    ç¼ł
    -0.21
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.64
     prepared
    0.56
    é¢Ħæ¡Ī
    0.51
    åĩĨå¤ĩå·¥ä½ľ
    0.49
    åĩĨå¤ĩ好
    0.49
    prepared
    0.48
     prepares
    0.48
     preparation
    0.47
     prepare
    0.47
     preparations
    0.47
    Activations Density 0.066%

    No Known Activations