© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    absolute value or quantity

    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
    主线
    -0.23
    éĹ°
    -0.19
    æĦıå¿Ĺ
    -0.19
    éļ½
    -0.18
    çĭĦ
    -0.18
     оÑĦоÑĢм
    -0.18
    imité
    -0.18
    	rv
    -0.17
    éĨį
    -0.17
    زع
    -0.17
    POSITIVE LOGITS
    ç»Ŀ对
    0.29
     absolute
    0.29
    æĢ»éĩı
    0.29
     relative
    0.28
    absolute
    0.26
    relative
    0.25
     volume
    0.24
     per
    0.23
    æķ´ä½ĵ
    0.22
    _absolute
    0.22
    Activations Density 0.148%

    No Known Activations