© 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. 10869
    Prev
    Next
    INDEX
    Explanations

    took

    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
    åĨ¢
    -0.19
    è¿Ļæĺ¯
    -0.18
    ird
    -0.18
    ä¸ĭéĿ¢å°±
    -0.17
    éĩįå¿ĥ
    -0.17
     overall
    -0.17
    ateg
    -0.17
    ÙĤÙĨ
    -0.17
    å¬ĸ
    -0.17
    olin
    -0.17
    POSITIVE LOGITS
    äºĨæĪijçļĦ
    0.41
    åľ¨æĪijçļĦ
    0.36
    æĪij家
    0.36
    ç»ĻäºĨæĪij
    0.34
     myself
    0.34
    对æĪijæĿ¥è¯´
    0.31
    æĪijåĴĮ
    0.31
    æĪijèĩªå·±
    0.31
    æĪijçļĦ
    0.30
    æĪijåľ¨
    0.30
    Activations Density 0.808%

    No Known Activations