© 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. 13904
    Prev
    Next
    INDEX
    Explanations

    cutting and slicing

    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
    å®¡æł¸
    -0.21
    æİĮ
    -0.19
    ilight
    -0.19
    åIJŁ
    -0.19
    лÑij
    -0.19
    ç»±
    -0.19
    æĸ°éĻĪ代谢
    -0.18
    äºĶçĻ¾
    -0.18
    æ§Į
    -0.18
    æ°¸ä¸į
    -0.18
    POSITIVE LOGITS
    åĪĩ
    0.25
    åĪĨåī²
    0.24
    åĪĩæĪIJ
    0.22
    ãģļ
    0.22
     slices
    0.22
    åĪĨæĪIJ
    0.21
    slice
    0.20
    å¡Ĭ
    0.20
    Utility
    0.19
    çŀ°
    0.19
    Activations Density 0.008%

    No Known Activations