© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    wanting help or information

    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
     establishes
    -0.24
    建ç«ĭäºĨ
    -0.24
    å°ģéĿ¢
    -0.24
    unden
    -0.23
    èģĶåIJĪ
    -0.22
    unga
    -0.22
     Intelligent
    -0.21
     establishing
    -0.21
    åı¬åĶ¤
    -0.21
    -author
    -0.21
    POSITIVE LOGITS
    æĢ¥éľĢ
    0.35
    æĥ³çŁ¥éģĵ
    0.33
    å¸ĮæľĽèĥ½å¤Ł
    0.30
     wanting
    0.29
     ingin
    0.28
    å¸ĮæľĽèĥ½
    0.28
    éĥ½æĥ³
    0.27
    ä¸įæĥ³
    0.27
     hoping
    0.26
    楽ãģĹãģ¿
    0.26
    Activations Density 0.898%

    No Known Activations