© 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. 10960
    Prev
    Next
    INDEX
    Explanations

    said this before

    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
    Ãłnh
    -0.20
    ä¸Ģ代
    -0.18
    å·¥
    -0.18
    ä¸ĭä¸Ģ代
    -0.18
    éŀį
    -0.17
    å§Ķå±Ī
    -0.17
    è°¤
    -0.17
    roit
    -0.17
    .zh
    -0.17
    çĻ½çĻ½
    -0.17
    POSITIVE LOGITS
    说è¿ĩ
    0.28
    èĮ¸
    0.21
    åįģåŃĹ
    0.19
    ä½łä¹Ł
    0.19
    asca
    0.19
    ä¸Ģéģį
    0.19
    ÑĭÑĪ
    0.18
    çļĦä¿¡ä»»
    0.18
    çĤĴä½ľ
    0.18
    çļĦ主é¢ĺ
    0.17
    Activations Density 0.114%

    No Known Activations