© 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. 16722
    Prev
    Next
    INDEX
    Explanations

    Daily Values, XML, LD50

    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
    åŀĽ
    -0.19
    åĸĩ
    -0.19
    pon
    -0.18
    ropol
    -0.18
     Kum
    -0.18
    erd
    -0.18
    пÑĢÑıжен
    -0.17
     обÑĢаÑĤ
    -0.17
    æĸ°åįİ
    -0.17
     Baghd
    -0.17
    POSITIVE LOGITS
    EOF
    0.22
    æĨ¬
    0.21
    æ¶ĤæĬ¹
    0.19
    åĽ´çĿĢ
    0.19
    á»ĥu
    0.18
     dealloc
    0.18
    æĿ³
    0.18
    éĶ·
    0.18
    饱åĴĮ
    0.17
    对人ä½ĵ
    0.17
    Activations Density 0.001%

    No Known Activations