© 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. 14087
    Prev
    Next
    INDEX
    Explanations

    oops, oh, yikes

    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
    /browse
    -0.20
    è¾ĭ
    -0.20
    ä¸įçĽ¸ä¿¡
    -0.19
    ä¸į解
    -0.19
    è¯Ł
    -0.18
    zing
    -0.18
    åħħæ²Ľ
    -0.18
    çĹ
    -0.18
    quist
    -0.17
    onn
    -0.17
    POSITIVE LOGITS
    éĢļçŁ¥
    0.20
    æľīçļĦ
    0.19
    chaft
    0.19
    ä¸įå°ıå¿ĥ
    0.19
    éŀŃ
    0.19
    ely
    0.18
    æ¼ı
    0.18
    ä¹ĭ举
    0.18
    draft
    0.18
    ibly
    0.18
    Activations Density 0.008%

    No Known Activations