© 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. 14158
    Prev
    Next
    INDEX
    Explanations

    Julius Ceasar

    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
    åĪĨè¡Į
    -0.21
    é»ĺ
    -0.20
    èµ°å»Ĭ
    -0.19
     Aud
    -0.19
     Audit
    -0.18
    æİł
    -0.18
     auditing
    -0.18
    象
    -0.18
    审计
    -0.18
    \base
    -0.18
    POSITIVE LOGITS
    éĤ£æł·çļĦ
    0.20
    imd
    0.19
    аÑİÑĤÑģÑı
    0.19
     solicit
    0.18
    ortex
    0.18
    Õ²
    0.18
    æĭ³
    0.18
    åĿļåĨ³
    0.17
     McMahon
    0.17
    åģıåIJij
    0.17
    Activations Density 0.003%

    No Known Activations