© 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. 12284
    Prev
    Next
    INDEX
    Explanations

    deal talks summit process negotiations

    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
    èĭ±æīį
    -0.23
    äºĨä¸Ģåı£
    -0.21
    library
    -0.20
    á»ij
    -0.20
    åĨĽåĽ¢
    -0.20
    mutable
    -0.19
    åħ¢
    -0.19
    èį£èªī
    -0.19
    feed
    -0.19
    æĺ¯ä¸Ģéĥ¨
    -0.19
    POSITIVE LOGITS
     talks
    0.22
     meetings
    0.21
    åįĩ温
    0.21
     démarch
    0.21
    ä¼ļè°Ī
    0.21
     démarche
    0.20
     bÃłn
    0.20
    uddle
    0.19
    è¿Ľç¨ĭ
    0.19
    对è¯Ŀ
    0.19
    Activations Density 0.021%

    No Known Activations