© 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. 12914
    Prev
    Next
    INDEX
    Explanations

    ester compounds

    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
     lod
    -0.21
     Expedition
    -0.21
    èĭĩ
    -0.20
    é¹°
    -0.20
    é«ĺåİŁ
    -0.20
    æľīåħ´è¶£
    -0.20
    unbind
    -0.19
     Everest
    -0.19
    毳
    -0.19
     ÐŁÐ°
    -0.19
    POSITIVE LOGITS
    梨
    0.33
    æ°´æŀľ
    0.23
    æ¡ĥ
    0.23
     apples
    0.23
     pear
    0.21
    æ²½
    0.21
    (iOS
    0.20
     apple
    0.20
    èĭ¹æŀľ
    0.19
    éĨª
    0.19
    Activations Density 0.114%

    No Known Activations