© 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. 12133
    Prev
    Next
    INDEX
    Explanations

    YouTube URLs

    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
    пÑĢакÑĤик
    -0.24
    ÑĩÑĢежден
    -0.22
    à¸Ħà¸ĵะà¸ģรรม
    -0.22
    RIPT
    -0.22
    ICODE
    -0.21
     ünl
    -0.20
     DERP
    -0.20
    à¸Ħะà¹ģà¸Ļ
    -0.20
    индивид
    -0.20
    еÑģÑĤеÑģÑĤвенн
    -0.20
    POSITIVE LOGITS
    æį¢ä¸ª
    0.21
    âģĥ
    0.20
    èĥ¡åŃIJ
    0.19
    åħĪæĬĬ
    0.19
     kayna
    0.19
    âĶŀ
    0.18
    æŀķ头
    0.18
     bÅĤ
    0.18
    æĢª
    0.18
    åı¦ä¸Ģä½į
    0.18
    Activations Density 0.098%

    No Known Activations