© 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. 11286
    Prev
    Next
    INDEX
    Explanations

    referrals and spreading information

    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
    è¯Ī
    -0.21
    ç¦ıç¥ī
    -0.20
    Ending
    -0.20
    æĶ¹éĿ©
    -0.20
    æ°ĶåĢĻåıĺåĮĸ
    -0.20
    æıĸ
    -0.19
    åĽĽé¡¹
    -0.19
    çļĦåIJĦ项
    -0.19
    对å¤ĸå¼ĢæĶ¾
    -0.19
    æĤ¬æĮĤ
    -0.19
    POSITIVE LOGITS
    åı£ç¢ij
    0.30
     ÑģеÑĤи
    0.21
    èĩªè§ī
    0.21
     cases
    0.20
     generation
    0.20
    æķĪåºĶ
    0.20
    Marketing
    0.19
    ä»ĸ人
    0.19
    pread
    0.18
    marketing
    0.18
    Activations Density 0.011%

    No Known Activations