© 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. 12847
    Prev
    Next
    INDEX
    Explanations

    new bsd license

    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
    åĨħçļĦ
    -0.20
     sola
    -0.17
    æĹ¢è¦ģ
    -0.17
    累累
    -0.16
    assin
    -0.16
    iola
    -0.16
    åīįèĢħ
    -0.16
    ummer
    -0.15
     misma
    -0.15
    æľĢåIJİ
    -0.15
    POSITIVE LOGITS
    bies
    0.40
    -found
    0.33
    swire
    0.31
     york
    0.31
    tons
    0.28
    ness
    0.27
    foundland
    0.27
    /new
    0.26
    ork
    0.25
    bie
    0.25
    Activations Density 0.175%

    No Known Activations