© 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. 12304
    Prev
    Next
    INDEX
    Explanations

    justice and healthcare systems

    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
    çĽijäºĭ
    -0.22
    æĹ¥åIJİ
    -0.22
    åİ¿å§Ķ书记
    -0.21
    åħ³èģĶ交æĺĵ
    -0.21
    ä¸Ģç·
    -0.20
    æĮģå¹³
    -0.20
    社ä¼ļ稳å®ļ
    -0.20
    éĤ¦
    -0.19
    æ¾Ħæ¸ħ
    -0.19
    æīĢåľ¨
    -0.19
    POSITIVE LOGITS
     system
    0.40
    ä½ĵç³»
    0.36
    ç³»ç»Ł
    0.35
    -system
    0.31
    ãĤ·ãĤ¹ãĥĨãĥł
    0.30
    ç³»ç»ŁçļĦ
    0.29
    system
    0.29
     système
    0.28
     systems
    0.28
     sistema
    0.28
    Activations Density 0.072%

    No Known Activations