© 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. 16147
    Prev
    Next
    INDEX
    Explanations

    ethylene and propylene

    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
    åħ·ä½ĵæĥħåĨµ
    -0.19
    æ¸į
    -0.18
    红åĨĽ
    -0.18
    èĥ½å¤Łåľ¨
    -0.18
    UCE
    -0.18
    éªĮ
    -0.18
    离èģĮ
    -0.18
    è°ģçŁ¥éģĵ
    -0.18
    åħ·ä½ĵçļĦ
    -0.18
    å¼±çĤ¹
    -0.18
    POSITIVE LOGITS
     cann
    0.24
    obox
    0.20
    æĢ»æĬķèµĦ
    0.19
    éķ¿å¤§
    0.19
    éĩįçĶŁ
    0.19
     reactor
    0.19
    วา
    0.19
    ование
    0.19
    举åĬ¨
    0.18
    çħ¤æ°Ķ
    0.18
    Activations Density 0.102%

    No Known Activations