© 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. 16870
    Prev
    Next
    INDEX
    Explanations

    DOI.org/ or /m, /s, /j, /e

    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
    ITO
    -0.19
    ırım
    -0.19
    à¸ĵ
    -0.19
    RIGHT
    -0.18
    åĽŀæĶ¶
    -0.18
    orate
    -0.18
    å°±æĺ¯è¦ģ
    -0.18
    æ¸
    -0.18
    Er
    -0.17
    APPER
    -0.17
    POSITIVE LOGITS
     Hutchinson
    0.19
    贵宾
    0.19
    泡沫
    0.19
    客æ°Ķ
    0.18
    å¯Įæ°ij
    0.18
    леп
    0.18
    åħļæĶ¿
    0.18
    头åıij
    0.18
     sag
    0.18
    æģ¶æĢ§
    0.18
    Activations Density 0.047%

    No Known Activations