© 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. 16314
    Prev
    Next
    INDEX
    Explanations

    mobile devices and platforms

    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
    åĩºåħ¥
    -0.21
    éļıæŶ
    -0.21
    æ´¾
    -0.20
    èµŀåĬ©
    -0.19
     ìŀħ
    -0.19
    omanip
    -0.19
    å¤ĦåĪĨ
    -0.19
     sẵ
    -0.19
    缴æĴŃéĹ´
    -0.19
    çļĦè·Ŀ离
    -0.18
    POSITIVE LOGITS
     Marr
    0.23
    æĺ¯ä»ĸ
    0.23
    éĩİå¿ĥ
    0.22
    æİĢ
    0.22
    jab
    0.21
    é¢ĨåŁŁ
    0.20
    phony
    0.20
    æĹ¥çĽĬ
    0.20
    çĶŁæľº
    0.20
    åĸ§
    0.19
    Activations Density 0.013%

    No Known Activations