© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2364
    Prev
    Next
    INDEX
    Explanations

    multiple variations

    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
    ä½Ĩä¹Ł
    -0.26
    ãģĭãĤĤ
    -0.24
    ãģıãģł
    -0.23
    以èĩ³äºİ
    -0.23
    éĤ£åĦ¿
    -0.23
    å¾Ģäºĭ
    -0.21
    å®ŀæĸ½ç»ĨåĪĻ
    -0.21
     elsewhere
    -0.21
    æ±Ģ
    -0.21
    /../
    -0.20
    POSITIVE LOGITS
    å¤ļ个
    0.35
    å¤ļç§į
    0.32
     multiple
    0.32
     different
    0.31
    ä¸įåIJĮçļĦ
    0.30
    ä¸įåIJĮ
    0.29
    以ä¸ĭåĩłä¸ª
    0.26
    两ç§į
    0.26
     twin
    0.25
     pairs
    0.24
    Activations Density 0.009%

    No Known Activations