© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15134
    Prev
    Next
    INDEX
    Explanations

    junior championship competitions

    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
    èĽ¹
    -0.22
    è¾±
    -0.20
    èݼ
    -0.20
    ä¸įåĪĨ
    -0.19
     puck
    -0.18
    座ä½į
    -0.18
     fog
    -0.18
    åīª
    -0.17
    åIJĦåįķä½į
    -0.17
     sme
    -0.17
    POSITIVE LOGITS
    anium
    0.19
    _Valid
    0.19
    rb
    0.19
    ç¾İ女
    0.19
    éªĿ
    0.18
    [vi
    0.18
     اÙĦÙħÙĦ
    0.18
    è¿ĻæĶ¯
    0.18
     Girls
    0.18
    lds
    0.18
    Activations Density 0.013%

    No Known Activations