© 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. 1589
    Prev
    Next
    INDEX
    Explanations

    selection of variety

    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
    ground
    -0.24
    ä¸Ģ段
    -0.24
    è¿Ļ段
    -0.24
    æľŃ
    -0.23
     bil
    -0.23
    neh
    -0.23
    \Annotation
    -0.22
    oho
    -0.22
    Evt
    -0.22
    //{{
    -0.22
    POSITIVE LOGITS
    丰å¯ĮçļĦ
    0.43
    丰å¯Į
    0.42
    èĥ½æ»¡è¶³
    0.38
    è±IJå¯Į
    0.38
    å¤ļæł·æĢ§
    0.38
     assortment
    0.38
     diversity
    0.36
    ç§įç±»
    0.36
    å¤ļæł·
    0.35
     Diversity
    0.35
    Activations Density 0.061%

    No Known Activations