© 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. 12674
    Prev
    Next
    INDEX
    Explanations

    Industry associations and organizations

    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
    SPELL
    -0.21
    å¥Ķ
    -0.20
    tober
    -0.20
    æ²»çIJĨ
    -0.20
    éħµ
    -0.20
    失败
    -0.19
    æ³Ĭ
    -0.19
    åĬ©åѦ
    -0.19
     disen
    -0.19
     Concord
    -0.18
    POSITIVE LOGITS
    åıįæĺłäºĨ
    0.21
    æĹĹä¸ĭçļĦ
    0.21
    æĹĹä¸ĭ
    0.20
     Sv
    0.20
    gross
    0.19
    LICENSE
    0.19
    代表
    0.19
    åħ¨äº§ä¸ļéĵ¾
    0.19
    ducers
    0.19
    éħįåIJĪ
    0.19
    Activations Density 0.032%

    No Known Activations