© 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. 14056
    Prev
    Next
    INDEX
    Explanations

    corpus luteum fertility

    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
    lass
    -0.19
    edImage
    -0.18
    DN
    -0.18
    èĥ½åĬĽåĴĮ
    -0.18
    羸
    -0.18
    åĩıè½»
    -0.17
    æ¾ľ
    -0.17
    æĥ«
    -0.17
    lash
    -0.17
    åģĩæĹ¥
    -0.17
    POSITIVE LOGITS
    è¾ħåĬ©
    0.20
    çĶŁæ®ĸ
    0.20
    æ¼ł
    0.20
    åĭĥ
    0.20
    è°·
    0.19
    ledo
    0.19
    åĥĸ
    0.19
    ä¿Ŀåį«
    0.19
    æ²Ń
    0.19
    æ¾Ħ
    0.18
    Activations Density 0.009%

    No Known Activations