© 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. 11135
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES of America

    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
    å·¥ä¸ļ大åѦ
    -0.19
    tha
    -0.19
    å°ĨæĿ¥
    -0.18
    为ä¹ĭ
    -0.18
     Colum
    -0.17
    ëĮĢë¡ľ
    -0.17
    RIES
    -0.17
    ahl
    -0.17
    .dk
    -0.17
    uit
    -0.16
    POSITIVE LOGITS
    æĹłåĬ©
    0.20
    ivities
    0.19
     bottled
    0.19
    edException
    0.17
    ÙĬÙĤ
    0.17
    ä¸įæŃ»
    0.17
    å£ħ
    0.17
    itsu
    0.16
    èĹıçĿĢ
    0.16
    unload
    0.16
    Activations Density 0.002%

    No Known Activations