© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    illness and infection cases

    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
    çļĩ宫
    -0.23
    ãģķãģĦ
    -0.20
    AsString
    -0.19
    icap
    -0.19
    odule
    -0.19
    advert
    -0.18
    _Internal
    -0.18
    ä½ĵåŀĭ
    -0.18
     Swe
    -0.18
    贯穿
    -0.18
    POSITIVE LOGITS
    æĬķè¯ī
    0.24
    æ±Ģ
    0.23
     lut
    0.21
    é¤IJæ¡Į
    0.21
    é£Łçī©
    0.21
     faint
    0.21
    VIP
    0.20
    å¸Ĥæ°ij
    0.20
    é£ŁçĶ¨
    0.19
    ç½ķè§ģ
    0.19
    Activations Density 0.065%

    No Known Activations