© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 674
    Prev
    Next
    INDEX
    Explanations

    Mitt Romney or Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    å¾Īä½İ
    -0.20
    /rem
    -0.20
    åħ¶ä»ĸåĽ½å®¶
    -0.20
    ãģĶãģĸ
    -0.19
     meth
    -0.19
     Wilkinson
    -0.19
     Ñģебе
    -0.19
    tte
    -0.19
     posted
    -0.19
    å¥
    -0.19
    POSITIVE LOGITS
    orse
    0.23
    强硬
    0.23
    -president
    0.22
    Obama
    0.21
    اء
    0.21
    临æŶ
    0.21
    standing
    0.21
    imizer
    0.21
    shire
    0.20
    ert
    0.20
    Activations Density 0.004%

    No Known Activations