© 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. 16540
    Prev
    Next
    INDEX
    Explanations

    judges and jury awards

    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
     brut
    -0.20
    èĤĦ
    -0.20
    ä¸Ĭè°ĥ
    -0.20
    obook
    -0.19
    calc
    -0.19
    èįª
    -0.19
    責
    -0.19
    ·»
    -0.18
    ç¿»
    -0.18
    ilate
    -0.18
    POSITIVE LOGITS
    å§Ķåijĺä¼ļ
    0.27
    è¯Ħå§Ķ
    0.24
    ä¸ī人
    0.23
    éĺµå®¹
    0.23
    å§Ķåijĺ
    0.20
    è¯Ħ审
    0.20
    ä¸Ģèĩ´
    0.20
    饮æĸĻ
    0.20
     panel
    0.19
    è¯Ħ
    0.19
    Activations Density 0.008%

    No Known Activations