© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    job titles and departments

    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
    ãģ³
    -0.26
    è«ĸ
    -0.23
    site
    -0.23
    yyy
    -0.22
     conjug
    -0.22
    åįļä¼ļ
    -0.21
    exit
    -0.21
    undle
    -0.21
     passive
    -0.20
    endet
    -0.20
    POSITIVE LOGITS
     department
    0.55
    éĥ¨éŨ
    0.54
    è´Łè´£äºº
    0.47
    ä¸ĵåijĺ
    0.46
    department
    0.44
    åĬŀåħ¬å®¤
    0.42
     manager
    0.42
    åĽ¢éĺŁ
    0.42
     Department
    0.42
    å·¥ç¨ĭå¸Ī
    0.42
    Activations Density 0.185%

    No Known Activations