© 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. 11761
    Prev
    Next
    INDEX
    Explanations

    interfaith, comparative, interprofessional, intersex

    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
    ãģ»ãģĨ
    -0.25
    è¾¼ãģ¾ãĤĮ
    -0.20
    OrUpdate
    -0.19
     ÙħÙĨÙĩ
    -0.18
    ãģĭãģij
    -0.17
    è¨ĺå¾Ĺ
    -0.17
    潦
    -0.17
    decltype
    -0.17
     Cisco
    -0.16
    çĭ¬çī¹çļĦ
    -0.16
    POSITIVE LOGITS
    åİĨæŶ
    0.23
    åĴĮåľ°åĮº
    0.22
    移åĪ°
    0.21
    åĬŀåħ¬åİħ
    0.20
    æį
    0.20
    icide
    0.20
    æľįåĬ¡ä¸Ńå¿ĥ
    0.19
    主ä¹ī
    0.19
    ä¹ĭéĹ´
    0.19
    æĪĸå¤ļ
    0.19
    Activations Density 0.034%

    No Known Activations