© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 16561
    Prev
    Next
    INDEX
    Explanations

    numbers 7

    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
     Legisl
    -0.19
    pch
    -0.18
    巨大
    -0.18
     sơ
    -0.17
    æ¼³
    -0.17
    åĬŁçİĩ
    -0.17
    éĻįä½İæĪIJæľ¬
    -0.17
    dirty
    -0.17
     cooperation
    -0.17
    å·¥æľŁ
    -0.17
    POSITIVE LOGITS
    stral
    0.22
    onas
    0.20
    .qq
    0.20
    ä¸įåıĬ
    0.19
    ä»ĭ
    0.19
    èľĹ
    0.19
    inal
    0.18
     tips
    0.18
    èĮ«
    0.18
    å¼ķ
    0.18
    Activations Density 0.005%

    No Known Activations