© 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. 16480
    Prev
    Next
    INDEX
    Explanations

    those of us who

    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
    äºĮåŃĹ
    -0.19
    ÑıÑĤÑģÑı
    -0.19
    çļĦå°±æĺ¯
    -0.19
    滨å·ŀ
    -0.19
    è¿ĻåIJį
    -0.18
    roit
    -0.17
    ç¶ļãģį
    -0.17
    è§ĩ
    -0.17
    åĬĪ
    -0.17
    çķĮçļĦ
    -0.16
    POSITIVE LOGITS
    ander
    0.22
    æľī
    0.21
    avel
    0.20
    åľ¨
    0.20
    yar
    0.19
    æĹ¥å¸¸
    0.19
     ÐĶмиÑĤÑĢ
    0.19
    usc
    0.19
    æĢĢçĿĢ
    0.18
    åħ´è¶£
    0.18
    Activations Density 0.010%

    No Known Activations