© 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. 1675
    Prev
    Next
    INDEX
    Explanations

    body parts, left, right, his, her

    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
    (mem
    -0.25
    TXT
    -0.25
    å¿ĥæĦı
    -0.24
    å½¢å¼ı
    -0.23
    .mem
    -0.23
    taire
    -0.23
     yazılı
    -0.22
    çļĦèī¯å¥½
    -0.22
    çİ°éĺ¶æ®µ
    -0.22
    èĢĮä¸įæĺ¯
    -0.22
    POSITIVE LOGITS
     mascul
    0.25
     left
    0.24
     reportedly
    0.24
    èĨĿçĽĸ
    0.24
    éĤ£åıª
    0.24
    мол
    0.23
     Fem
    0.23
     rear
    0.23
    tring
    0.23
    åīįç½®
    0.23
    Activations Density 0.016%

    No Known Activations