© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    academic pursuits and degrees

    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
    鸣
    -0.27
    é²ľæĺİ
    -0.24
    åĩºåİĤ
    -0.23
    åĩ«
    -0.23
    è§ģéĿ¢
    -0.23
     decor
    -0.22
    è¿ĻéĩĮæľī
    -0.22
    è´´å¿ĥ
    -0.22
    åıijå¸ĥåħ¬åijĬ
    -0.22
     customizable
    -0.22
    POSITIVE LOGITS
    åѦåİĨ
    0.31
     coursework
    0.28
    大ä¸ĵ
    0.28
    vit
    0.27
     Psychology
    0.27
    åŃ¦è´¹
    0.27
    å¿ĥçIJĨåѦ
    0.27
     college
    0.26
     university
    0.26
    è¿Ľä¿®
    0.26
    Activations Density 0.038%

    No Known Activations