© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or letters followed by commas

    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
     ÐŁÐ¾Ñĩем
    -0.28
     ÐIJлекÑģан
    -0.27
     поÑģколÑĮ
    -0.25
     ÑĦоÑĢмиÑĢова
    -0.22
    ÑĩÑĢежден
    -0.21
     ÐĶмиÑĤÑĢ
    -0.21
     пÑĥÑĤеÑĪ
    -0.20
    æĻ®éģį
    -0.20
    ÏĬ
    -0.19
     пÑĢиÑıÑĤн
    -0.19
    POSITIVE LOGITS
     etc
    0.22
    æĭįæĭį
    0.21
    åĨįåĪ°
    0.20
    åĿĬ
    0.20
    (phase
    0.20
    /english
    0.20
    çŃīéĥ¨éŨ
    0.19
    æ¯ıèĤ¡
    0.18
    uckle
    0.18
    åĵ¥ä»¬
    0.18
    Activations Density 0.165%

    No Known Activations