© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    community organizations

    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
    æĪIJ为ä¸ĢåIJį
    -0.23
    è¾ĵåįµç®¡
    -0.20
    é»ijå¤ľ
    -0.20
    æĺ¯ä¸ĢåIJį
    -0.20
    è¿Ŀæ³ķè¡Į为
    -0.19
    ìĤ½
    -0.19
     Laud
    -0.19
    æĺ¯ä¸Ģä½į
    -0.19
    æĭľå¸Ī
    -0.18
    ãĤĴä¸İ
    -0.18
    POSITIVE LOGITS
    iscal
    0.21
     Trom
    0.21
    ÑĢай
    0.20
     worldwide
    0.20
     profile
    0.19
    åľ¨é¦Ļ港
    0.19
    çĥŃ
    0.19
    åĨ¬
    0.18
    æī§
    0.18
    åľ¨ä¸ŃåĽ½
    0.18
    Activations Density 0.016%

    No Known Activations