© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12608
    Prev
    Next
    INDEX
    Explanations

    Interleukin, Olympic results, race times

    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
     pres
    -0.22
    ruk
    -0.22
     ÐŁÐ¾Ñĩем
    -0.21
     ÐIJлекÑģан
    -0.20
     Macron
    -0.20
    cem
    -0.20
    ileo
    -0.19
    acas
    -0.19
    permanent
    -0.19
     ÐĶмиÑĤÑĢ
    -0.19
    POSITIVE LOGITS
    女åŃIJ
    0.21
    è¶Ĭéĩİ
    0.20
    äºīåĪĽ
    0.19
     ÑģеÑĤ
    0.19
    交éĢļå®īåħ¨
    0.18
    æĹłäºº
    0.18
    ä½ĵéªĮ
    0.18
    ampion
    0.18
    èݲèĬ±
    0.18
    éķ¿éĢĶ
    0.18
    Activations Density 0.005%

    No Known Activations