© 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. 15154
    Prev
    Next
    INDEX
    Explanations

    result in

    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
    è¿Ļç§įæĸ¹å¼ı
    -0.19
    åıijå±ķåīįæĻ¯
    -0.19
    åĦ¿
    -0.19
    äºĴè¡¥
    -0.18
    индив
    -0.18
    ÑĢеги
    -0.18
    irty
    -0.18
    индивид
    -0.18
    è¿Ļç§įæĸ¹æ³ķ
    -0.18
    imag
    -0.17
    POSITIVE LOGITS
    çļĦç»ĵæŀľ
    0.24
    äºĨä¸Ģç³»åĪĹ
    0.23
    ä¸Ģç³»åĪĹ
    0.23
     forth
    0.23
     oluÅŁan
    0.22
    äºĨä¸Ģåľº
    0.21
    ä¹İ
    0.20
    大æī¹
    0.20
    èħł
    0.19
    大éĩıçļĦ
    0.19
    Activations Density 0.055%

    No Known Activations