© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    financial and legal services

    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
    èĤĨ
    -0.21
    permanent
    -0.20
    ä¸įæĸŃçļĦ
    -0.18
     perman
    -0.18
    驱
    -0.18
     Diss
    -0.18
    æĶ¿æĿĥ
    -0.18
    èĩ´å¯Į
    -0.18
    ivate
    -0.18
    éģ¥æݧ
    -0.18
    POSITIVE LOGITS
    æī¿
    0.23
    å¤ļ家
    0.21
    icip
    0.20
    æŃ¦å£«
    0.20
    è£
    0.20
    åĩłå®¶
    0.20
    æĬ¥åijĬæľŁåĨħ
    0.20
     Greenwich
    0.20
    åīįç½®
    0.20
    éĩijèŀįæľºæŀĦ
    0.20
    Activations Density 0.007%

    No Known Activations