© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14893
    Prev
    Next
    INDEX
    Explanations

    pillowcases, cushions, furniture covers

    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
    vey
    -0.20
    翳
    -0.19
    梳
    -0.19
    æµģæ°´
    -0.19
    .Branch
    -0.19
    çħİ
    -0.19
    é¬ĵ
    -0.18
    ysics
    -0.18
    èĴ¸
    -0.18
    移éĢģ
    -0.18
    POSITIVE LOGITS
    åŃ£èĬĤ
    0.24
    è¡¥åħħ
    0.23
    ç»ĦåIJĪ
    0.21
     aqu
    0.20
    éĩĩæļĸ
    0.20
    ä¸ļ主
    0.19
    -shell
    0.19
    èĵ¼
    0.19
    å°ģ
    0.19
     pool
    0.19
    Activations Density 0.004%

    No Known Activations