© 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. 14216
    Prev
    Next
    INDEX
    Explanations

    law professor title

    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
    мел
    -0.23
    è¿Ļ家åħ¬åı¸
    -0.22
    г
    -0.21
    ä¸ŃåĽ½åĪ¶éĢł
    -0.21
    åī¯åİ¿éķ¿
    -0.21
    è¿Ļ家
    -0.21
    воз
    -0.20
    vari
    -0.20
    代çIJĨåķĨ
    -0.20
    åħ¥æĪ·
    -0.20
    POSITIVE LOGITS
    æī§ä¸ļ
    0.30
    å¾ĭå¸Ī
    0.28
     juris
    0.27
    æ³ķåѦ
    0.26
     attorneys
    0.25
     lawyers
    0.24
     lawyer
    0.24
    åĬŀæ¡Ī
    0.24
     Gins
    0.24
     Constitutional
    0.23
    Activations Density 0.056%

    No Known Activations