© 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. 13255
    Prev
    Next
    INDEX
    Explanations

    photo by or photo:

    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
    undy
    -0.21
    ledon
    -0.18
    лад
    -0.17
    缴æݥ影åĵį
    -0.17
    å¾®éĩı
    -0.17
     proceed
    -0.17
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.17
    ocate
    -0.17
    é¢Ĩ
    -0.17
    å§ij
    -0.17
    POSITIVE LOGITS
    éĻIJãĤĬ
    0.21
    Flex
    0.21
     Flex
    0.20
    个交æĺĵæĹ¥
    0.19
     Action
    0.19
    è®°èĢħåľ¨
    0.19
    akan
    0.19
    被éªĹ
    0.19
     ACTION
    0.18
    æ±´
    0.18
    Activations Density 0.032%

    No Known Activations