© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    medical imaging

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Complete
    -0.26
    etically
    -0.26
     Vanilla
    -0.25
    åĩºç¤º
    -0.23
     оÑĤдÑĭÑħ
    -0.23
    æ¸ļ
    -0.23
    plete
    -0.22
    Clone
    -0.22
    Premium
    -0.22
     Latitude
    -0.22
    POSITIVE LOGITS
    å§Ķåijĺä¼ļ
    0.34
     Institute
    0.33
     Committee
    0.33
    çłĶ究ä¸Ńå¿ĥ
    0.33
     committee
    0.33
     Council
    0.31
     Center
    0.30
     Association
    0.30
    åįıä¼ļ
    0.30
     Department
    0.29
    Activations Density 0.253%

    No Known Activations