© 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. 15649
    Prev
    Next
    INDEX
    Explanations

    future outcomes or possibilities

    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
    è´¯
    -0.28
    ä»İæĿ¥æ²¡æľī
    -0.22
    貫
    -0.21
    åĪ°å¤Ħ
    -0.20
    åŁ
    -0.20
    æł¹æľ¬ä¸į
    -0.20
    æ¯ıå½ĵ
    -0.20
    æĬĢæľ¯åĴĮ
    -0.20
    贯穿
    -0.20
    åģļè¿ĩ
    -0.20
    POSITIVE LOGITS
    渺
    0.22
    Aligned
    0.21
     win
    0.20
    æĭ¿ä¸ĭ
    0.20
    åĪĩéĻ¤
    0.19
    edian
    0.19
    å¾Ģä¸Ĭ
    0.19
    pliers
    0.19
    angs
    0.18
    èµ¢å¾Ĺ
    0.18
    Activations Density 0.020%

    No Known Activations