© 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. 15497
    Prev
    Next
    INDEX
    Explanations

    ships, vessels, and watercraft

    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
    æ·±å¤Ħ
    -0.21
    åı¯æĥ³èĢĮçŁ¥
    -0.21
    以人为
    -0.21
    ç¼°
    -0.20
    çĤĻ
    -0.19
    emp
    -0.19
    è¿ĻäºĽäºº
    -0.19
    ние
    -0.19
    éĤ¾
    -0.18
     pers
    -0.18
    POSITIVE LOGITS
    ä¸ĵéĹ¨ä¸º
    0.21
    综åIJĪä½ĵ
    0.20
    管çIJĨæĿ¡ä¾ĭ
    0.20
    海峡
    0.19
    èį©
    0.18
    é£İåħī
    0.18
    ç³»åĪĹ
    0.18
    èĤ¡æĿĥ
    0.18
    å®ļä»·
    0.18
    /pub
    0.18
    Activations Density 0.020%

    No Known Activations