© 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. 13076
    Prev
    Next
    INDEX
    Explanations

    love for

    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
     наÑĢко
    -0.22
    天èĬ±æĿ¿
    -0.18
    ifiers
    -0.18
    alking
    -0.18
    iasi
    -0.18
    ç»ĦæĪIJéĥ¨åĪĨ
    -0.17
    ä¸įèī¯ä¿¡æģ¯
    -0.17
    产ä¸ļåįĩ级
    -0.17
    ANTI
    -0.17
     rq
    -0.17
    POSITIVE LOGITS
    0.24
    ç¥ĸåĽ½
    0.20
    ä¼łç»ŁçļĦ
    0.20
    å·²ä¹ħ
    0.20
    è¿IJåĬ¨
    0.20
    éĴ»çłĶ
    0.20
    ä¸įå·²
    0.19
     intact
    0.19
     underst
    0.19
    大海
    0.19
    Activations Density 0.034%

    No Known Activations