© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2355
    Prev
    Next
    INDEX
    Explanations

    events occurring shortly after

    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
    ize
    -0.24
    æĸ¹éĿ¢çļĦ
    -0.24
    çĶŁçĶŁ
    -0.23
    ial
    -0.23
    è¶³å¤Ł
    -0.23
    åħħåĪĨåıijæĮ¥
    -0.23
    æľĢç»Ī
    -0.23
    ful
    -0.23
    æĸ¹éĿ¢
    -0.23
     meantime
    -0.22
    POSITIVE LOGITS
    æľ¬ç½ij
    0.23
    被åĪĹåħ¥
    0.22
    髦
    0.22
     possessing
    0.21
    å®ĥçļĦ
    0.21
    è¸ıä¸Ĭ
    0.21
    edBy
    0.21
    社ä¼ļåıijå±ķ
    0.21
     attempting
    0.20
    idis
    0.20
    Activations Density 0.024%

    No Known Activations