© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    introduction this

    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
    ãī
    -0.19
    注æĺİåĩºå¤Ħ
    -0.19
    azar
    -0.19
    èĪįä¸įå¾Ĺ
    -0.19
    ãĥļãĥ³
    -0.18
    è¿°èģĮ
    -0.18
    ä¸ĩæĪ·
    -0.18
    注éĶĢ
    -0.17
    èĭķ
    -0.17
    ãĤĭãģ¹ãģį
    -0.17
    POSITIVE LOGITS
     [âĢ¦]
    0.18
    æĸ°çļĦ
    0.17
    çļĦæĺ¯
    0.17
    iÄĻ
    0.17
    \"
    0.16
    âĢļ
    0.16
    ､
    0.16
    âĢŁ
    0.16
    平淡
    0.16
    âĢ¦âĢ¦
    0.16
    Activations Density 0.117%

    No Known Activations