© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    Professor titles and names

    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
    CDATA
    -0.25
    \Php
    -0.24
    ä¸įä¸ĭ
    -0.23
    åħŃ大
    -0.23
    (Arrays
    -0.23
    ä¸įåIJĮæĦı
    -0.22
    ahi
    -0.22
     Ah
    -0.22
    ään
    -0.22
    æįķæįī
    -0.22
    POSITIVE LOGITS
     endowed
    0.34
     professor
    0.32
     Faculty
    0.31
     faculty
    0.29
    åŃ¦æľ¯
    0.28
     lecturer
    0.27
     doctoral
    0.27
    åѦèĢħ
    0.26
     Professor
    0.26
     Lect
    0.26
    Activations Density 0.035%

    No Known Activations