© 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. 13715
    Prev
    Next
    INDEX
    Explanations

    PUBLIC "-//W3C//DTD XHTML

    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
    åIJŁ
    -0.21
    ndef
    -0.20
    å¼Ĥåľ°
    -0.20
    ìĬ¹
    -0.20
    æĭ©
    -0.19
    è§ı
    -0.19
    èĬĤæĹ¥
    -0.19
    è®©æĽ´å¤ļ
    -0.18
    ention
    -0.18
    iteur
    -0.18
    POSITIVE LOGITS
    çĶļ
    0.21
    çŃīåĽłç´ł
    0.19
    (optional
    0.19
    帽
    0.18
    æIJŃ
    0.18
    åIJĦæľī
    0.18
    åIJĦèĩª
    0.18
     Probe
    0.18
    ellen
    0.18
    ãģĿãĤĮãģŀãĤĮ
    0.17
    Activations Density 0.002%

    No Known Activations