© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12477
    Prev
    Next
    INDEX
    Explanations

    removal of content

    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
    ially
    -0.19
    åī¯ä¸»ä»»
    -0.17
    沤
    -0.17
    鸱
    -0.16
    å¾Ī强
    -0.16
    emet
    -0.16
    åįģ足
    -0.16
    anton
    -0.16
    ìŀĪëĬĶ
    -0.16
    vice
    -0.15
    POSITIVE LOGITS
    æİī
    0.33
    æİīäºĨ
    0.28
    åIJİçļĦ
    0.26
    ä¸įäºĨ
    0.25
    æ®Ĩ
    0.25
    äºĨ许å¤ļ
    0.24
    çİĩ
    0.22
    äºĨèĩªå·±çļĦ
    0.22
    äºĨä»ĸçļĦ
    0.21
    å¤ļä½ĻçļĦ
    0.21
    Activations Density 0.267%

    No Known Activations