© 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. 2367
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
    åIJįåı«
    -0.28
    pan
    -0.28
    otor
    -0.26
     Called
    -0.24
    第äºĮ天
    -0.24
     Instead
    -0.24
    ot
    -0.23
     called
    -0.23
    aci
    -0.23
    called
    -0.23
    POSITIVE LOGITS
    ä½ķåĨµ
    0.36
    æĽ´ä½ķåĨµ
    0.30
    ä»»ä½ķ人
    0.27
    åĨµä¸Ķ
    0.26
    ä½Ĩ对äºİ
    0.26
    åѦçĶŁä»¬
    0.26
    ä½ĨæĪij们
    0.25
     fountain
    0.24
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
     endforeach
    0.24
    Activations Density 0.191%

    No Known Activations