© 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. 2393
    Prev
    Next
    INDEX
    Explanations

    new narrative or paradigm

    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
    åĬłçıŃ
    -0.28
     timings
    -0.27
     warranty
    -0.26
     timed
    -0.26
    çİ°åľº
    -0.25
    ä¸ĬéŨ
    -0.24
    urchased
    -0.24
     consecutive
    -0.24
    æĬ½æŁ¥
    -0.23
     favorite
    -0.23
    POSITIVE LOGITS
    éĩįæŀĦ
    0.52
    åħ¨æĸ°çļĦ
    0.42
    çIJĨ念
    0.42
     redefine
    0.39
     rethink
    0.39
    æĽ¿ä»£
    0.38
     radically
    0.38
     parad
    0.38
    æĢĿç»´æĸ¹å¼ı
    0.38
    æĸ°æ¨¡å¼ı
    0.38
    Activations Density 0.100%

    No Known Activations