© 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. 13148
    Prev
    Next
    INDEX
    Explanations

    year

    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
    .lu
    -0.24
    åªĴ
    -0.21
    erset
    -0.21
    zell
    -0.20
    atk
    -0.19
    atively
    -0.19
    Charsets
    -0.18
    åĬŁèĥ½æĢ§
    -0.18
     Spicer
    -0.18
     Enjoy
    -0.18
    POSITIVE LOGITS
    å¤ļå±Ĥ次
    0.20
    åįİ润
    0.20
    å±Ĥ次
    0.19
     ÑĢож
    0.19
    è¿Ļä¹Ł
    0.19
    æijĨåľ¨
    0.19
    åıĺå¾Ĺ
    0.18
    çĶŁæĦı
    0.18
    escal
    0.18
    æĹłæīĢè°ĵ
    0.18
    Activations Density 0.265%

    No Known Activations