© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    time of day or date

    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
    æı½
    -0.21
    人æµģ
    -0.21
    обоÑĢ
    -0.21
    endar
    -0.21
    ä¸ĢèĦļ
    -0.20
    turn
    -0.19
    该æĢİä¹ĪåĬŀ
    -0.19
    Cumhur
    -0.18
    ÑİÑĤ
    -0.18
     TAX
    -0.18
    POSITIVE LOGITS
    äu
    0.19
     Trot
    0.19
    èķī
    0.19
    è´£ç¼ĸ
    0.18
     Hills
    0.18
    zet
    0.18
     Indust
    0.18
     HAPP
    0.17
    æł¡
    0.17
     pet
    0.17
    Activations Density 0.032%

    No Known Activations