© 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. 15402
    Prev
    Next
    INDEX
    Explanations

    caused by

    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
    çīĿ
    -0.24
    íĹĢ
    -0.21
    edor
    -0.20
     miÄĻd
    -0.20
    _ComCallableWrapper
    -0.20
    天使
    -0.19
    å¿łå®ŀ
    -0.19
    âīĤ
    -0.19
     mükem
    -0.19
    aylight
    -0.19
    POSITIVE LOGITS
    åݲ
    0.24
    å¼ķèµ·çļĦ
    0.24
     causing
    0.22
    è¢Ńåĩ»
    0.21
    ä¿Ĺ称
    0.21
    侵害
    0.21
    éĢłæĪIJçļĦ
    0.20
    -ca
    0.20
     strains
    0.19
    æīĢèĩ´
    0.19
    Activations Density 0.294%

    No Known Activations