© 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. 11011
    Prev
    Next
    INDEX
    Explanations

    Grand Canyon State

    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
    éĿ©
    -0.22
    大éģĵ
    -0.20
    éĥijéĩį
    -0.20
    ç¥Ń
    -0.20
    éĵĽ
    -0.20
    etas
    -0.20
    etz
    -0.20
     жиз
    -0.19
    èĩ§
    -0.19
    å°ıæŶåīį
    -0.19
    POSITIVE LOGITS
     empt
    0.20
    âĪħ
    0.19
     measuring
    0.19
    æľĢ好ä¸įè¦ģ
    0.19
    oid
    0.19
    Mit
    0.18
    åĪ°åºķæĺ¯
    0.18
     Mit
    0.18
    æĹ¢èĥ½
    0.18
    -interest
    0.17
    Activations Density 0.010%

    No Known Activations