© 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. 12401
    Prev
    Next
    INDEX
    Explanations

    Obama administration proposals

    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
    çĽ²
    -0.23
    æİ¥å¾ħ
    -0.23
    æĬĹæĭĴ
    -0.21
    è¦Ĩ
    -0.21
    æĬ¥éħ¬
    -0.21
    elo
    -0.20
    asco
    -0.20
    çĵ¯
    -0.20
    åķĨåľĪ
    -0.20
    çłĶ
    -0.20
    POSITIVE LOGITS
    éĩįçĤ¹é¢ĨåŁŁ
    0.22
     initiatives
    0.21
    æľķ
    0.21
    .multipart
    0.21
    ç¼¥
    0.20
    quez
    0.19
    ogi
    0.19
    衽
    0.19
    亲èĩª
    0.19
    multipart
    0.19
    Activations Density 0.057%

    No Known Activations