© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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
    rams
    -0.21
    ahu
    -0.21
    .lu
    -0.20
    aurus
    -0.20
     Pey
    -0.20
    åī§éĻ¢
    -0.19
    _meter
    -0.19
    yte
    -0.19
    ohon
    -0.19
    篷
    -0.19
    POSITIVE LOGITS
     commercially
    0.31
    èĩªå¸¦
    0.29
    æĿ¥èĩª
    0.26
     imported
    0.23
     myself
    0.22
    å¤ĸæı´
    0.21
    http
    0.21
    à¸Īาà¸ģ
    0.21
    https
    0.21
    ä¾Ĩèĩª
    0.21
    Activations Density 0.433%

    No Known Activations