© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    maritime affairs

    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
    ingly
    -0.31
    desk
    -0.27
    inator
    -0.22
    maker
    -0.22
    makers
    -0.22
    ä¸İåıijå±ķ
    -0.21
    sheet
    -0.21
    é¥Ńèıľ
    -0.21
    åĴĮåıijå±ķ
    -0.21
    toc
    -0.21
    POSITIVE LOGITS
    zee
    0.28
    å·¥ä½ľèĢħ
    0.25
    çĶ¨åĵģ
    0.25
     affairs
    0.24
    ä¹ĭæĺŁ
    0.23
    ä¹ĭç¾İ
    0.23
    ä¹ĭåĬĽ
    0.23
    人士
    0.23
     counterparts
    0.23
     warfare
    0.22
    Activations Density 0.045%

    No Known Activations