© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    reportedly introduced or mentioned

    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
    /misc
    -0.27
    itional
    -0.26
    eco
    -0.25
    æľīä¸Ģå®ļçļĦ
    -0.25
    ä»İåݻ年
    -0.24
    eworthy
    -0.24
     misc
    -0.24
    misc
    -0.23
     Especially
    -0.23
    éĢ²ä¸ĢæŃ¥
    -0.23
    POSITIVE LOGITS
     famously
    0.36
     reportedly
    0.32
    åIJĵå¾Ĺ
    0.30
     aston
    0.29
     astonished
    0.28
     legendary
    0.28
    西è£ħ
    0.27
     hilar
    0.26
     arrog
    0.26
    éĵ¸
    0.26
    Activations Density 0.068%

    No Known Activations