© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    absorbent articles / diapers

    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
    庸
    -0.21
    ildo
    -0.21
    硼
    -0.20
    -exec
    -0.19
    çĽ²çĽ®
    -0.19
    åı¤æĢª
    -0.19
     Lamp
    -0.18
    èij¡èIJĦ
    -0.18
    åĶ¤éĨĴ
    -0.18
    éĽī
    -0.18
    POSITIVE LOGITS
    åŁĿ
    0.25
    åŀ«
    0.25
     diapers
    0.23
    骶
    0.21
     disposable
    0.20
    责任åĪ¶
    0.20
    èĩĬ
    0.20
    å¤ĸåĮħ
    0.20
    ç§ijæĬĢèĤ¡ä»½
    0.19
    èł²
    0.19
    Activations Density 0.030%

    No Known Activations