© 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. 15364
    Prev
    Next
    INDEX
    Explanations

    at first glance

    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
    ä¸ĭ次
    -0.23
    éļıæŶ
    -0.21
    ä¹ĭæīĢ以
    -0.20
    æѤæŶ
    -0.20
    æīĢè°ĵ
    -0.19
    plusplus
    -0.18
    æĹ©æĹ¥
    -0.18
    ä¸ĭä¸ĢæŃ¥
    -0.18
    å±ĬæŶ
    -0.18
    缮åīįå·²
    -0.18
    POSITIVE LOGITS
     glance
    0.31
    ierce
    0.20
     sight
    0.20
    æĦŁè§ī
    0.20
    imers
    0.20
    è§īå¾Ĺ
    0.19
    ä¼ļè§īå¾Ĺ
    0.19
     blush
    0.19
    ä¸į太
    0.19
    grave
    0.18
    Activations Density 0.012%

    No Known Activations