© 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. 12752
    Prev
    Next
    INDEX
    Explanations

    Roosevelt and Hoover

    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
    éĢ¡
    -0.17
    onne
    -0.17
     Birmingham
    -0.16
    layer
    -0.16
    éĻIJãĤĬ
    -0.16
    æŃĮæīĭ
    -0.16
    scenes
    -0.15
    music
    -0.15
    knife
    -0.15
    oes
    -0.15
    POSITIVE LOGITS
    æĻļå¹´
    0.22
    æł·çļĦ
    0.19
    ÙĬات
    0.19
    gerald
    0.18
    platz
    0.18
    aled
    0.17
    佬
    0.17
    mega
    0.17
    oric
    0.17
    æ¤ħ
    0.17
    Activations Density 0.004%

    No Known Activations