© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    worship

    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
    ips
    -0.20
    lining
    -0.20
    SORT
    -0.19
    sort
    -0.19
    ially
    -0.19
    çİ©æĦı
    -0.19
    æī¾å·¥ä½ľ
    -0.19
    åĿŀ
    -0.18
    å§Ķ书记
    -0.18
    å¾Īå¤ļäºĭæĥħ
    -0.18
    POSITIVE LOGITS
    ful
    0.29
    èĢħ
    0.25
    fully
    0.24
    ä¹ĭä½Ļ
    0.22
    èĢħçļĦ
    0.22
    /pr
    0.21
    naire
    0.21
    æĶĺ
    0.21
    gether
    0.21
    acle
    0.21
    Activations Density 0.004%

    No Known Activations