© 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. 13533
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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
    大æ¦Ĥ
    -0.21
    ive
    -0.19
    ous
    -0.18
    amental
    -0.18
     overt
    -0.18
    é©·
    -0.17
    acent
    -0.17
    çľ¼çľĭ
    -0.17
    åIJĪçIJĨçļĦ
    -0.17
    好çļĦ
    -0.17
    POSITIVE LOGITS
    è¾IJ
    0.19
    uide
    0.18
    iets
    0.18
    çīĪæĿĥæīĢæľī
    0.18
     Lone
    0.18
    âĩij
    0.18
    第ä¸ī次
    0.18
    åī©
    0.17
    msp
    0.17
     Jose
    0.16
    Activations Density 0.076%

    No Known Activations