© 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. 11740
    Prev
    Next
    INDEX
    Explanations

    PHP mysqli queries

    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
     Telegram
    -0.23
    çħ¤æ°Ķ
    -0.20
    家å±ŀ
    -0.20
    解åĨ³éĹ®é¢ĺ
    -0.19
    åĬŀçIJĨ
    -0.19
    èĢģ人
    -0.19
     telegram
    -0.18
    离éĢĢä¼ij
    -0.18
    StateException
    -0.18
     elderly
    -0.18
    POSITIVE LOGITS
    аÑĢи
    0.20
     physic
    0.20
    eco
    0.19
     MacBook
    0.19
    èĩªçĦ¶èĢĮ
    0.19
    é«¡
    0.19
    å®ĺ宣
    0.18
    Ñıн
    0.18
     ministry
    0.18
    agra
    0.18
    Activations Density 0.003%

    No Known Activations