© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    time of day

    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
    _proof
    -0.19
    é²ĩ
    -0.19
    èŁ
    -0.19
    é³Ħ
    -0.18
    满满çļĦ
    -0.18
    achu
    -0.18
    车åĨħ
    -0.18
    оваÑĢ
    -0.18
    icked
    -0.18
    é²
    -0.17
    POSITIVE LOGITS
    大éĥ¨åĪĨ
    0.25
     ÙħعظÙħ
    0.22
     majority
    0.22
    鸳
    0.22
    æĥħ趣
    0.22
    大å¤ļæķ°
    0.22
    PHA
    0.22
    ç»Ŀ大éĥ¨åĪĨ
    0.21
     most
    0.21
    anson
    0.21
    Activations Density 0.170%

    No Known Activations