© 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. 11614
    Prev
    Next
    INDEX
    Explanations

    athletic and swimming events

    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
    æľĢ大åĮĸ
    -0.20
    ptr
    -0.19
    åĽ´è§Ĥ
    -0.19
    éĨ®
    -0.18
     RV
    -0.18
    åįĥåı¤
    -0.18
    KH
    -0.17
    éķ¿æŶéĹ´
    -0.17
    çļĦçIJĨ念
    -0.17
    -repeat
    -0.17
    POSITIVE LOGITS
    çł
    0.18
    温æ³ī
    0.18
    INAL
    0.18
    orical
    0.18
    oders
    0.18
    itta
    0.18
    lements
    0.17
    há»ķ
    0.17
    ibbean
    0.17
    _Framework
    0.17
    Activations Density 0.002%

    No Known Activations