© 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. 11390
    Prev
    Next
    INDEX
    Explanations

    ending in -ing

    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
    emann
    -0.20
    åĩĨåĪĻ
    -0.19
    åı¯æĥ³èĢĮçŁ¥
    -0.18
    èIJ½
    -0.17
    ç²¥
    -0.17
    zee
    -0.17
    å¾Ĺä½ı
    -0.17
    åIJ¯
    -0.17
    zag
    -0.17
    ä¸ĵåĮº
    -0.17
    POSITIVE LOGITS
    ections
    0.19
    sto
    0.18
    ÙĴ
    0.18
    ations
    0.18
    icies
    0.17
    metro
    0.17
    getManager
    0.17
    çŁŃ线
    0.17
    onest
    0.17
     деÑĤÑģк
    0.17
    Activations Density 0.901%

    No Known Activations