© 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. 11429
    Prev
    Next
    INDEX
    Explanations

    http://

    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
    æĭ¥
    -0.21
    ough
    -0.20
     loose
    -0.20
    AMA
    -0.19
    ︿
    -0.19
    åĬ©
    -0.19
     Loose
    -0.18
    adden
    -0.18
    æĹ¥æĻļ
    -0.17
    娱
    -0.17
    POSITIVE LOGITS
     Stall
    0.20
    è¿ĺå¾Ĺ
    0.20
    åıĪä¸Ģ次
    0.19
    形象
    0.19
    éĥijéĩį
    0.18
    è°±åĨĻ
    0.18
    hop
    0.18
    åIJĮæĥħ
    0.18
    isphere
    0.18
    bite
    0.18
    Activations Density 0.073%

    No Known Activations