© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    extracting or unpacking files

    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
    idon
    -0.19
    转弯
    -0.19
    aint
    -0.19
    scriptId
    -0.18
    illes
    -0.18
    Ace
    -0.18
    æijĦ
    -0.18
    åģı离
    -0.18
    éĩ
    -0.18
    chie
    -0.18
    POSITIVE LOGITS
     unfolding
    0.23
    åıĸåĩº
    0.23
    è¿ĺåİŁ
    0.23
     unzip
    0.22
    解å¼Ģ
    0.21
     Organizer
    0.21
    å±ķå¼Ģ
    0.21
    æĸĩ件
    0.21
    æıIJåıĸ
    0.21
    ä¸Ģ大åłĨ
    0.21
    Activations Density 0.036%

    No Known Activations