© 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. 16902
    Prev
    Next
    INDEX
    Explanations

    at a location or event

    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
    жал
    -0.20
    ours
    -0.20
    ниÑĨа
    -0.20
    çĶ¨å¾®ä¿¡
    -0.19
    reen
    -0.19
    fty
    -0.19
    俱ä¹IJ
    -0.18
    кÑĤ
    -0.18
    ters
    -0.18
    asser
    -0.18
    POSITIVE LOGITS
    åľºåIJĪ
    0.23
    åį³å°ĨåĪ°æĿ¥
    0.22
    ä¸ºæľŁ
    0.22
    äºĨä¸Ģåľº
    0.21
    ç§ĭ
    0.20
    第ä¸Ģå±Ĭ
    0.20
    æľĢåIJİä¸Ģ次
    0.20
    çļĦè¯Ŀ
    0.20
     upcoming
    0.20
    YLE
    0.19
    Activations Density 0.046%

    No Known Activations