© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15340
    Prev
    Next
    INDEX
    Explanations

    police reports she said

    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
    æĽ´æĸ°
    -0.20
    侧éĩį
    -0.20
     bandwidth
    -0.19
    äºĴè¡¥
    -0.19
    æ±ī
    -0.19
     today
    -0.19
    calar
    -0.18
    带
    -0.18
     our
    -0.18
     spectrum
    -0.18
    POSITIVE LOGITS
    ãģĿãģ®å¾Į
    0.23
    建档ç«ĭåį¡
    0.23
    éļıåIJİ
    0.21
    ä»ĸåıĪ
    0.21
    严éĩįçļĦ
    0.20
    被æī§è¡Į
    0.20
    女æĸ¹
    0.20
    ä¹Ĥ
    0.20
    认å®ļ
    0.20
    çļĦè¡£æľį
    0.20
    Activations Density 0.048%

    No Known Activations