© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    file names with image extensions

    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
    rem
    -0.24
    éĤ£æł·çļĦ
    -0.20
     rem
    -0.20
    缸åıį
    -0.20
    åķ¦
    -0.20
    yen
    -0.19
    erman
    -0.19
    ing
    -0.19
     pil
    -0.19
     ${({
    -0.19
    POSITIVE LOGITS
    æĢ»éĿ¢ç§¯
    0.21
    æĦ¤æĢĴ
    0.21
    åħħå®ŀ
    0.20
    侦æİ¢
    0.20
    éĩİå¿ĥ
    0.20
    psc
    0.19
    WITHOUT
    0.19
    æŃ£ä¹ī
    0.19
    壮è§Ĥ
    0.19
    æĸĩæ¡£
    0.19
    Activations Density 0.019%

    No Known Activations