© 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. 13406
    Prev
    Next
    INDEX
    Explanations

    exclusivity and limitation

    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
    èķ¤
    -0.20
    尽头
    -0.20
    æ¯ıä¸Ģ个人
    -0.19
    åħ·ä½ĵçļĦ
    -0.19
    çļĦåħ·ä½ĵ
    -0.19
     differently
    -0.19
    duk
    -0.18
    èĭ±
    -0.18
    icken
    -0.18
    æľīä¸įåIJĮçļĦ
    -0.18
    POSITIVE LOGITS
    exclusive
    0.25
    åĶ¯ä¸Ģ
    0.25
     exclus
    0.23
    æĢ§çļĦ
    0.23
     exclusive
    0.21
    åĶ¯ä¸ĢçļĦ
    0.21
    æĥŁ
    0.21
    Exclusive
    0.21
     sole
    0.20
    çĭ¬å®¶
    0.20
    Activations Density 0.058%

    No Known Activations