© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    include or list of people

    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
     gre
    -0.21
    æĵį
    -0.19
    广
    -0.18
    æ³ł
    -0.17
    å§Ķ
    -0.17
    Quote
    -0.17
     quote
    -0.17
    iley
    -0.17
    ati
    -0.17
    å°½
    -0.17
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.36
    åĴĮæĬĢæľ¯
    0.30
    åĴĮ
    0.23
    åıĬ缸åħ³
    0.23
    åĴĮåľ°åĮº
    0.22
    _and
    0.22
    åıĬ
    0.21
     ÙĪاÙĦÙģ
    0.19
    æĥ¯
    0.19
    à¹ģละ
    0.19
    Activations Density 0.701%

    No Known Activations