© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1085
    Prev
    Next
    INDEX
    Explanations

    non-stick, vegetable, extra-virgin, margarine, shortening, distilled water

    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
    velope
    -0.25
     extraordin
    -0.24
    çļĦæ¦Ĥ念
    -0.24
    æ¦Ĥ念
    -0.23
    åıijå±ķ模å¼ı
    -0.23
     çĶŁåij½åij¨æľŁ
    -0.23
    DataBase
    -0.23
     resembl
    -0.22
     Sovere
    -0.22
    åĺĺ
    -0.22
    POSITIVE LOGITS
     standard
    0.27
     preferably
    0.27
    çĶ¨éĩı
    0.26
    æłĩåĩĨ
    0.26
     Standard
    0.25
    Standard
    0.25
    举
    0.24
     Reid
    0.23
    NC
    0.23
    æݨèįIJ
    0.23
    Activations Density 0.037%

    No Known Activations