© 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. 13247
    Prev
    Next
    INDEX
    Explanations

    x86 architecture

    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
    liness
    -0.19
    berries
    -0.19
    å¢ĥ
    -0.19
    åłµå¡ŀ
    -0.19
    icip
    -0.18
    PELL
    -0.18
    luck
    -0.18
    ulk
    -0.18
    è¿Ľåı£
    -0.17
    orget
    -0.17
    POSITIVE LOGITS
    -based
    0.21
    UpDown
    0.18
    çīĪ
    0.18
    ä¼ģä¸ļæıIJä¾Ľ
    0.18
    çļĦ强大
    0.18
    tran
    0.18
    顶å°ĸ
    0.18
     ole
    0.17
    atomy
    0.17
    ause
    0.17
    Activations Density 0.030%

    No Known Activations