© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15806
    Prev
    Next
    INDEX
    Explanations

    printing and print-related terms and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    bjerg
    -0.20
    æ°´æ³µ
    -0.19
    è¯ķ管
    -0.19
    çłĶ究éĻ¢
    -0.19
    çŃ·åŃIJ
    -0.19
    htub
    -0.19
    è°ļ
    -0.18
    á»ijn
    -0.18
     Mess
    -0.18
    ëĦ·
    -0.18
    POSITIVE LOGITS
    åį°åĪ·
    0.42
    åĩºçīĪ
    0.35
     printing
    0.31
     print
    0.28
    Printing
    0.27
    /print
    0.27
    åį°
    0.27
     Printing
    0.26
    print
    0.26
    åıijè¡Į
    0.25
    Activations Density 0.041%

    No Known Activations