© 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. 13748
    Prev
    Next
    INDEX
    Explanations

    Down Syndrome and Florence

    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
    è¨Ģè¡Į
    -0.21
    æĦıæĢĿæĺ¯
    -0.21
    rons
    -0.21
    ATUS
    -0.19
    essel
    -0.19
    çĶ¨æ°´
    -0.18
    ä¸ĢåĪĩéĥ½
    -0.18
    èģĮ
    -0.18
    è¡Įäºĭ
    -0.18
    çĥģ
    -0.17
    POSITIVE LOGITS
     lover
    0.19
    ç§Ģ丽
    0.18
    /ne
    0.17
     воп
    0.17
    -Compatible
    0.17
     Brigham
    0.17
     Heck
    0.17
    çĽĬ
    0.17
    -enabled
    0.17
    åħ¨å±Ģ
    0.16
    Activations Density 0.004%

    No Known Activations