© 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. 16681
    Prev
    Next
    INDEX
    Explanations

    cup of

    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
    lux
    -0.19
    ynchronously
    -0.19
    aland
    -0.19
    æĻļå¹´
    -0.19
    rij
    -0.18
     Mods
    -0.18
    opus
    -0.18
    (skip
    -0.18
    æݨ
    -0.18
     forum
    -0.18
    POSITIVE LOGITS
    æĭĺ
    0.21
    éĩĬ
    0.21
    ä¸įç¡®å®ļæĢ§
    0.18
    fw
    0.18
    æºŁ
    0.18
    éĥĵ
    0.18
    æĹ¥å¸¸å·¥ä½ľ
    0.18
    顾
    0.17
     Estates
    0.17
    мел
    0.17
    Activations Density 0.066%

    No Known Activations