© 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. 49
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    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
     Hers
    -0.23
     Multip
    -0.22
     UNSIGNED
    -0.21
    Multip
    -0.20
    —but
    -0.20
     unborn
    -0.19
    å¼ķåıij
    -0.19
    "If
    -0.19
    emas
    -0.19
    anye
    -0.19
    POSITIVE LOGITS
    -wise
    0.36
    ä¹Łå¥½
    0.32
     vs
    0.31
    çļĦéĤ£ç§į
    0.30
    éĻ¤å¤ĸ
    0.29
     wise
    0.26
    æ¯ķç«Łæĺ¯
    0.26
     <->
    0.25
     =~
    0.25
    å½ĵçĦ¶æĺ¯
    0.25
    Activations Density 0.464%

    No Known Activations