© 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. 15721
    Prev
    Next
    INDEX
    Explanations

    resolution, offer, statement

    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
    çªij
    -0.23
    æ¯ıä¸Ģ个人
    -0.22
    çŀ³
    -0.22
    ä¸Ń级
    -0.22
    éĢłä»·
    -0.20
    å¾ģä¿¡
    -0.20
    çªł
    -0.19
    ç²¾æ¹Ľ
    -0.19
    建çŃijä¸ļ
    -0.19
    çĤķ
    -0.19
    POSITIVE LOGITS
    表åĨ³
    0.25
    æĬķ票
    0.25
    对åħ¬åı¸
    0.24
    åĨ³è®®
    0.23
    èĤ¡ä¸ľ
    0.23
    èĤ¡æĿĥ
    0.22
    æĦıè§ģ
    0.22
     mailed
    0.22
     voting
    0.22
    rimon
    0.21
    Activations Density 0.007%

    No Known Activations