© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50940
    Prev
    Next
    INDEX
    Explanations

    distance measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æ¯ıæľĪ
    -0.09
    æĶ¹æŃ£
    -0.08
    èĦ¾æ°Ķ
    -0.08
    è¡«
    -0.08
    acking
    -0.08
    æĸĩç«łæĿ¥æºIJ
    -0.08
    æĮİ
    -0.08
    .MiddleLeft
    -0.08
     Paste
    -0.08
    è·¨
    -0.08
    POSITIVE LOGITS
    è·Ŀ离
    0.17
    è·ĿéĽ¢
    0.15
    çļĦè·Ŀ离
    0.14
     distance
    0.13
    Distance
    0.13
    distance
    0.13
     distances
    0.12
     Distance
    0.12
    (distance
    0.12
    è·Ŀ
    0.12
    Activations Density 0.029%

    No Known Activations