© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3260
    Prev
    Next
    INDEX
    Explanations

    cannot guarantee

    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
    Negative Logits
    Inflater
    -0.25
    èµ°åIJij
    -0.24
     epic
    -0.23
    heels
    -0.23
     Trades
    -0.22
    åݻ买
    -0.22
     vain
    -0.22
    ailed
    -0.22
     Halifax
    -0.22
    å±ŀäºİ
    -0.22
    POSITIVE LOGITS
    æīĢæıIJä¾ĽçļĦ
    0.32
    æıIJä¾ĽçļĦ
    0.29
     advise
    0.29
     advice
    0.28
    æģķ
    0.28
     requests
    0.27
    请æĤ¨
    0.27
    è«ĭæĤ¨
    0.27
    åIJĦä½į
    0.27
    æīĢæıIJä¾Ľ
    0.26
    Activations Density 0.013%

    No Known Activations