© 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. 15561
    Prev
    Next
    INDEX
    Explanations

    arrival, strike, or fall

    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
    egis
    -0.20
    å¾Ĺåĩº
    -0.19
    åIJijä¸Ĭ
    -0.18
    ç»Į
    -0.18
    ext
    -0.18
     Weiter
    -0.18
    trait
    -0.17
    EIF
    -0.17
    endors
    -0.17
    为ä¸ŃåĽ½
    -0.17
    POSITIVE LOGITS
    éĻį临
    0.24
    åħ¨èº«
    0.23
    åĪ°ä½į
    0.21
    IDO
    0.21
    襲
    0.21
    æĿ¥ä¸´
    0.20
    ç£IJ
    0.20
     اÙĦرØŃ
    0.20
     us
    0.19
     domicile
    0.18
    Activations Density 0.034%

    No Known Activations