© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    pole for podium

    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
    æ³Ľ
    -0.19
    ç½ħ
    -0.19
    äºĶåħŃ
    -0.18
    主ä¸ļ
    -0.18
     Gone
    -0.18
     baff
    -0.18
    çĮ©
    -0.18
    éİ
    -0.18
    (calc
    -0.18
    骨头
    -0.18
    POSITIVE LOGITS
    åħ¥åľº
    0.27
    ä½įç½®
    0.23
    éĢĨè¢Ń
    0.23
    åĩºåıij
    0.23
    ä¸įåĪ©
    0.23
    绳
    0.20
    ãĤ¹ãĤ¿ãĥ¼ãĥĪ
    0.20
    é¦ĸä½į
    0.20
    第ä¸Ģä½į
    0.20
    VIRTUAL
    0.19
    Activations Density 0.018%

    No Known Activations