© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    television program

    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
    游æĪıè£ħå¤ĩ
    -0.24
    å¶Ļ
    -0.22
    åºĹ主
    -0.22
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.21
    æĿijæ°ij
    -0.21
    éĢīè´Ń
    -0.21
    俱ä¹IJ
    -0.20
    หลวà¸ĩ
    -0.20
    åºĹéĩĮ
    -0.20
    æݢ访
    -0.20
    POSITIVE LOGITS
    åĨħ容
    0.27
    GenerationStrategy
    0.27
    æĴŃåĩº
    0.26
    èĬĤ缮
    0.25
     content
    0.24
    DEFINE
    0.24
     ÑĢейÑĤ
    0.24
    ÑĩÑĢежден
    0.23
     поÑģколÑĮ
    0.23
    æĴŃ
    0.23
    Activations Density 0.109%

    No Known Activations