© 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. 11160
    Prev
    Next
    INDEX
    Explanations

    electrical connection pins

    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
    /he
    -0.20
    quisitions
    -0.19
    詹
    -0.19
    渲
    -0.19
    upt
    -0.19
    大å¥ĸ
    -0.19
    urred
    -0.18
    认å®ļ
    -0.18
    _bound
    -0.18
    кле
    -0.18
    POSITIVE LOGITS
    æĢ»æĶ¶åħ¥
    0.22
     caut
    0.21
    ÑĤок
    0.21
     incomplete
    0.20
    èĪĮå°ĸ
    0.20
    æĹłçŁ¥
    0.20
    Opens
    0.19
    产åѦ
    0.19
    íĤ¤
    0.19
    é½IJåħ¨
    0.19
    Activations Density 0.076%

    No Known Activations