© 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. 13967
    Prev
    Next
    INDEX
    Explanations

    trailer

    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
    æĻļå¹´
    -0.20
    tempt
    -0.17
    soever
    -0.17
    é¢Ķ
    -0.17
    åħ¸èĮĥ
    -0.16
    åIJĦæł·
    -0.16
    çķĻå®Ī
    -0.16
    éķĬ
    -0.16
     smugg
    -0.16
    achel
    -0.15
    POSITIVE LOGITS
    gage
    0.18
    ä¸ĬçļĦ
    0.17
    CUS
    0.17
    appl
    0.16
    abra
    0.16
    -mounted
    0.16
    age
    0.16
    åİ¢
    0.16
    aging
    0.15
    ãģĴ
    0.15
    Activations Density 0.005%

    No Known Activations