© 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. 3364
    Prev
    Next
    INDEX
    Explanations

    add or subtract

    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
    æĹĭ
    -0.24
     rotations
    -0.23
    ods
    -0.23
    .rdf
    -0.23
    ghi
    -0.23
    nga
    -0.22
     reversal
    -0.21
    Reverse
    -0.21
     rode
    -0.21
    -stat
    -0.21
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.32
     subtract
    0.31
     Subtract
    0.31
    æī£éĻ¤
    0.28
    (add
    0.27
    subtract
    0.26
     addUser
    0.26
    宿
    0.26
     extra
    0.25
     Adding
    0.25
    Activations Density 0.081%

    No Known Activations