© 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. 3400
    Prev
    Next
    INDEX
    Explanations

    sales, fins, mutations, windows, system, gap, Christian, travelling

    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
    yr
    -0.24
    è¿Ļä¸ĢåĪĩ
    -0.23
    侬
    -0.22
    ãģ»ãģĨ
    -0.22
     similarly
    -0.22
    æĬĬè¿ĻäºĽ
    -0.21
    ((_
    -0.21
     synd
    -0.20
     Busy
    -0.20
     vice
    -0.20
    POSITIVE LOGITS
    çŃīåĽłç´ł
    0.25
    ä¸įè§ģ
    0.23
    æĺı
    0.21
    å²Ľä¸Ĭ
    0.21
    Rotation
    0.21
     SMA
    0.21
    ç¥ŀç§ĺ
    0.20
    çŃīéĹ®é¢ĺ
    0.20
     rotations
    0.20
    ters
    0.20
    Activations Density 1.073%

    No Known Activations