© 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. 13160
    Prev
    Next
    INDEX
    Explanations

    prototype relating to function or concept

    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
    ings
    -0.22
     dÃłng
    -0.19
    fully
    -0.17
    adge
    -0.17
    rai
    -0.16
    INGS
    -0.16
    oya
    -0.15
    ç¼Ĺ
    -0.15
    /her
    -0.15
    ities
    -0.15
    POSITIVE LOGITS
    æľŁåĨħ
    0.20
    allee
    0.18
    èĪ¬çļĦ
    0.16
    æĢ§å¼º
    0.16
    rema
    0.16
    åĮĸçļĦ
    0.16
    atic
    0.15
    æĦıä¹īä¸ĬçļĦ
    0.15
    swith
    0.15
    ique
    0.15
    Activations Density 0.034%

    No Known Activations