© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12233
    Prev
    Next
    INDEX
    Explanations

    signature details

    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
    orr
    -0.20
    heroes
    -0.20
    item
    -0.19
    éĶĻ
    -0.18
    åħ±æľī
    -0.18
    ob
    -0.18
     brakes
    -0.18
    åľ¨æķ´ä¸ª
    -0.18
    arn
    -0.18
     st
    -0.17
    POSITIVE LOGITS
    peq
    0.22
     echang
    0.22
    æĬ¥ä»·
    0.19
     uLocal
    0.19
    注æĺİæĿ¥æºIJ
    0.19
     jes
    0.19
    ]init
    0.19
    åIJĦè¡ĮåIJĦ
    0.19
    ernel
    0.18
     sourceMapping
    0.18
    Activations Density 0.013%

    No Known Activations